DETAILED ACTION
This communication is a Non-Final Office Action rejection on the merits. Claims 1, 3-8, 10-15, and 17-22 are currently pending and have been addressed below.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 05/27/206 has been entered.
Response to Arguments
Applicant's arguments filed on 05/27/2026 (related to the 103 Rejection) have been fully considered but are moot in view of new grounds of rejection. Applicant's amendments necessitated the new ground(s) of rejection presented in this Office action. Rejection based on a newly cited reference(s) follows.
Applicant's arguments filed on 05/27/2026 (related to the 101 Rejection) have been fully considered but they are not persuasive.
Applicant states, on pages 14-20, that the claims are directed to a specific technical improvement in how ML models are configured, trained, and operationalized- not to the abstract idea of prediction itself. Also, the amended claims are directly analogous to Example 47, Claim 3 of the 2024 USPTO AI Guidance, which the Examiner identified a suggested model for patent-eligible ML claims. (1) A machine learning model that is not generic or black-box, but rather is specifically configured as a recurrent neural network having a plurality of initial layers - comprising an input layer, a long short-term memory (LSTM) layer, and a dropout layer - and a plurality of output layers, wherein the initial layers are shared across the output layers via a functional APL This architecture is specifically chosen to capture temporal dependencies and lag relationships inherent in sequential housing transaction data - a particularized technical solution to the problem of predicting home builder performance from noisy, low-volume, time-series data. See Application, FIG. 4 (ML model 400, layers 422, 424, 426, 430, 440). (2) A two-phase training process applying an optimization algorithm to a training dataset comprising both historical home transaction data and historical home demand data. (3) A bifurcated performance prediction comprising two distinct outputs: (i) a predicted number of home transactions for an upcoming time period, output by a first dense output layer, and (ii) a predicted change in home transactions expressed as a probability distribution over increase, decrease, and no-change outcomes output by a second tri-output dense layer applying a softmax activation function. (4) The instructions transmitted cause automatic execution of one or more specific remedial actions.
Examiner respectfully disagrees with Applicant. These claim elements are considered to be abstract ideas because they are directed to “certain methods of organizing human activity” which include “commercial or legal interactions.” In this case, tracking historic home transactions associated with the set of home builder communities is considered a sales activity (see MPEP 2106.04(a)(2)). If a claim limitation, under its broadest reasonable interpretation, covers commercial or legal interactions, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
The main functions of the additional elements recited in claim 1 are merely used to: collect data (e.g. historic home transactions associated with the set of home builder communities) and analyze the data (e.g. generate a performance prediction such as predicted number of home transactions). Those are functions that the courts have described as merely indicating a field of use or technological environment in which to apply a judicial exception (see MPEP 2106.05(h)). Also, the additional element of a machine learning is merely used to generate a home sales prediction. The trained ML model may include a plurality of initial layers, a first final layer, and a second final layer. According to aspects, the home sales prediction may include a predicted number of home sales for a time period and a predicted change in home sales from a previous time period to the time period (Paragraphs 0020 & 0082-0084). This element of “machine learning comprising a recurrent neural network” is recited at a high level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer element (MPEP 2106.05f). In this case, the machine learning includes inputs (e.g., historical home transaction data and historical home demand data associated with a set of home builder communities) and outputs (e.g., a predicted number of home transactions and a predicted change in home transactions). Although the specification states that the machine learning model is trained to predict performance for home builders, the claim and specification lacked specific details about how the trained machine learning model operates (e.g., how the recurrent neural network is learning a specific sequence). Thus, the analysis/learning step of the model is a black box, which is merely claiming the idea of a solution or outcome (MPEP 2106.05(a)). Also, the step of “receiving home status” is considered a conventional computer function of “receiving or transmitting data over a network” and “performing repetitive calculations” (MPEP 2106.05d). The step of “automatic execution of one or more remedial actions” does not impose any meaningful limits on the judicial exception, which results in an insignificant extra-solution activity (MPEP 2106.05(g)). Therefore, Examiner notes that claim 1 is still similar to example 47, claim 2 of July 2024 AI Subject Matter Eligibility.
Lastly, the claim fails to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, adding unconventional steps that confine the claim to a particular useful application, and/or meaningful limitations beyond generally linking the use of an abstract idea to a particular environment. See 84 Fed. Reg. 55. Viewed individually or as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself. The claim is ineligible.
Independent claims 8 and 15 recite similar features and therefore are rejected for the same reasons as independent claim 1. Claims 3-7, 10-14, and 17-22 are rejected for having the same deficiencies as those set forth with respect to the claims that they depend from, independent claims 1, 8, and 15.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 3-8, 10-15, and 17-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without reciting significantly more.
Independent Claim 1
Step One - First, pursuant to step 1 in the January 2019 Revised Patent Subject Matter Eligibility Guidance (“2019 PEG”) on 84 Fed. Reg. 53, the claim 1 is directed to an apparatus which is a statutory category.
Step 2A, Prong One - Claim 1 recites: A system for dynamic performance tracking for home builders, the system to perform the steps of: training a model on historical home transaction data and historical home demand data associated with a set of home builder communities, wherein training the model comprises a training dataset comprising the historical home transaction data and the historical home demand data in a first training phase and a second training phase; receiving home status data for the set of home builder communities, wherein a home builder community of the set of home builder communities comprises a respective set of homes, and wherein the home status data comprises at least a completion status for homes of the set of home builder communities, a set of historical performance data for the set of home builder communities, and a target metric; determining a set of target paces associated with the set of home builder communities based on the home status data, where a target pace of the set of target paces is associated with completed home transactions for homes within a respective home builder community during a selected time period; receiving performance data associated with the set of home builder communities, wherein the performance data indicates historic home transactions associated with the set of home builder communities; extracting a plurality of features from the home status data and the performance data to generate a set of feature vectors comprising a numerical representation of the plurality of features; providing the set of feature vectors as input to the model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, and (ii) a predicted change in home transactions output as a probability distribution over increase, decrease, and no-change outcomes; comparing the set of target paces to the performance data to determine a respective performance metric for the home builder community of the set of home builder communities; and transmitting a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction, wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: adjusting a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities. These claim elements are considered to be abstract ideas because they are directed to “certain methods of organizing human activity” which include “commercial or legal interactions.” In this case, tracking historic home transactions associated with the set of home builder communities is considered a sales activity (see MPEP 2106.04(a)(2)). If a claim limitation, under its broadest reasonable interpretation, covers commercial or legal interactions, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 - The judicial exception is not integrated into a practical application. Claim 1 includes additional elements: a memory; a processor coupled to the memory; a machine learning model comprising a recurrent neural network having a plurality of initial layers and a plurality of output layers, and wherein the plurality of initial layers are shared across the plurality of output layers; an optimization algorithm; a first node of a network; and a second node of the network.
The memory is merely used to store instructions (Paragraph 0047). The processor is merely used to execute instructions (Paragraph 0047). The trained ML model may include a plurality of initial layers, a first final layer, and a second final layer. According to aspects, the home sales prediction may include a predicted number of home sales for a time period and a predicted change in home sales from a previous time period to the time period (Paragraphs 0020 & 0082-0084). The optimization algorithm is merely used to converge to a prediction quickly when used for the massive number of features that may be included in sequenced data (Paragraph 0086). The first node of a network is merely used to receive home status data and performance data (Paragraphs 0007 & 0009). The second node of a network is merely used to transmit a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities (Paragraph 0011). Merely stating that the step is performed by a computer component results in “apply it” on a computer (MPEP 2106.05f). These elements of “memory,” “processor,” “machine learning model,” “optimization algorithm,” and “first and second node” are recited at a high level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer element. Also, the nodes of the network are considered “insignificant extra-solution activity” (MPEP 2106.05g) since they are used for necessary data gathering and outputting (e.g., gathering statistics to generate performance metrics). Accordingly, alone and in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, the claim is directed to an abstract idea.
Step 2B - The claim does not include additional elements that are sufficient to amount significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the claims describe how to generally “apply” the concept of updating a price based on a performance prediction. The specification shows that the memory is merely used to store instructions (Paragraph 0047). The processor is merely used to execute instructions (Paragraph 0047). The trained ML model may include a plurality of initial layers, a first final layer, and a second final layer. According to aspects, the home sales prediction may include a predicted number of home sales for a time period and a predicted change in home sales from a previous time period to the time period (Paragraphs 0020 & 0082-0084). The optimization algorithm is merely used to converge to a prediction quickly when used for the massive number of features that may be included in sequenced data (Paragraph 0086). The first node of a network is merely used to receive home status data and performance data (Paragraphs 0007 & 0009). The second node of a network is merely used to transmit a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities (Paragraph 0011). In this case, the machine learning includes inputs (e.g., historical home transaction data and historical home demand data associated with a set of home builder communities) and outputs (e.g., a predicted number of home transactions and a predicted change in home transactions). Although the specification states that the machine learning model is trained to predict performance for home builders, the claim and specification lacked specific details about how the trained machine learning model operates (e.g., how the recurrent neural network is learning a specific sequence). Thus, the analysis/learning step of the model is a black box, which is merely claiming the idea of a solution or outcome (MPEP 2106.05(a)). Also, the step of “receiving home status” is considered a conventional computer function of “receiving or transmitting data over a network” and “performing repetitive calculations” (MPEP 2106.05d). The step of “automatic execution of one or more remedial actions” does not impose any meaningful limits on the judicial exception, which results in an insignificant extra-solution activity (MPEP 2106.05(g)). Thus, nothing in the claim adds significantly more to the abstract idea. The claim is ineligible.
Examiners recommends to further specify how the machine learning operates (e.g., how the recurrent neural network is learning a sequence). Please follow 2024 AI Guidance, Example 47, Claim 3.
Independent claim 8 is directed to a process at step 1, which is a statutory category. Claim 8 recites similar limitations as claim 1 and is rejected for the same reasons at step 2a, prong one; step 2a, prong 2; and step 2b. Thus, the claim is ineligible.
Independent claim 15 is directed to an article of manufacture at step 1, which is a statutory category. Claim 15 recites similar limitations as claim 1 and is rejected for the same reasons at step 2a, prong one; step 2a, prong 2; and step 2b. Claim 15 further recites a non-transitory computer readable medium – which is treated as just an explicit “processor/computer” for storing and executing the operations and is treated under MPEP 2106.05f in the same manner as claim 1. Accordingly, this additional element of “non-transitory computer readable medium” is viewed as “apply it on a computer” at step 2a, prong 2 and step 2b. Thus, the claim is ineligible.
Dependent claims 3-5, 10-12, and 17-18 are not directed to any additional claim elements. Rather, these claims offer further descriptive limitations of the abstract idea mentioned above - such as: wherein the representation of the performance metric for a first home builder community indicates whether the first home builder community is ahead of a target pace associated with the first home builder community, meeting the target pace, or behind the target pace; wherein being ahead of the target pace comprises having a historical performance metric of historical home transaction data more than 0.5 home transactions above the target pace, meeting the target pace comprises having a historical performance metric within 0.5 home transactions of the target pace, and being behind the target pace comprises having a historical performance metric more than 0.5 home transactions below than the target pace; wherein the completion status for each home of the set of home builder communities indicates that a given home is scheduled to be built, within a first building phase, within a second building phase, or fully built; and wherein the historical performance metric comprises an average historical performance over a period of time. These processes are similar to the abstract idea noted in the independent claim because they further the limitations of the independent claim which are directed to certain methods of organizing human activity which include managing personal behavior. In this case, the new limitations are merely describing how the performance metric is compared to a target (e.g., analyzing historical information). In addition, there are no additional elements to consider at Step 2A Prong 2 and Step 2B. Therefore, the claims still recite an abstract idea that can be grouped into certain methods of organizing human activity.
Dependent claims 6, 13, and 19 are not directed to any additional claim elements. Rather, these claims offer further descriptive limitations of elements found in the independent claims and addressed above - such as: receive a user input that includes the selected time period. These processes are similar to the abstract idea noted in the independent claim because they further the limitations of the independent claim which are directed to a method of organizing human activity which include managing personal behavior. The additional function of the GUI is merely used to receive a user input. This GUI is considered “field of use” (MPEP 2106.05h) at step 2A, Prong 2; as it’s just used to receive information, but does not improve the GUI. At Step 2B, this is conventional still, “receiving or transmitting data over a network” (MPEP 2106.05d). Thus, nothing in the claim adds significantly more to the abstract idea. The claim is ineligible.
Dependent claims 7, 14, and 20 are not directed to any additional claim elements. Rather, these claims offer further descriptive limitations of elements found in the independent claims and addressed above - such as performing at least one of the following steps: tracking the performance data for a home builder community and dynamically updating the respective target pace and performance metric for the home builder community based on the tracking; receiving additional home status data for new homes in a home builder community and dynamically updating the target pace and performance metric based on the additional home status data; receiving the home status data from a client device, a proprietary feed, a public data source, a first data source, or a combination thereof; receiving the performance data from a client device, a public performance data source or feed; a second data source, or a combination thereof; or outputting to the GUI a representation of the home status data. These processes are similar to the abstract idea noted in the independent claim because they further the limitations of the independent claim which are directed to a method of organizing human activity which include managing personal behavior. The additional functions are considered “field of use” (MPEP 2106.05h) at step 2A, Prong 2; as they are just used to receive additional information, but does not improve the technology. At Step 2B, this is conventional still, “receiving or transmitting data over a network” and “performing repetitive calculations” (MPEP 2106.05d). Thus, nothing in the claim adds significantly more to the abstract idea. The claim is ineligible.
Dependent claims 21 and 22 are not directed to any additional claim elements. Rather, these claims offer further descriptive limitations of elements found in the independent claims and addressed above - such as to: receive one or more user inputs; present a predicted increase graph; present a predicted decrease graph; and present a predicted no change graph. These processes are similar to the abstract idea noted in the independent claim because they further the limitations of the independent claim which are directed to a method of organizing human activity which include managing personal behavior. The additional functions of the GUI are merely used to: receive a user input; and present a graphical representation. This GUI is considered “field of use” (MPEP 2106.05h) at step 2A, Prong 2; as it’s just used to receive information, but does not improve the GUI. At Step 2B, this is conventional still, “receiving or transmitting data over a network” (MPEP 2106.05d). Thus, nothing in the claim adds significantly more to the abstract idea. The claim is ineligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3-8, 10-15, and 17-21 are rejected under 35 U.S.C. 103 as being unpatentable over Bleakley et al. (US 2013/0346151 A1), in view of Lin et al. (US 2024/0070741 A1), in further view of Takamatsu et al. (US 2018/0082388 A1).
Regarding claim 1 (Currently Amended), Bleakley et al. discloses a system for dynamic performance tracking for home builders, the system comprising (Abstract, The systems and methods can use automated valuation models (AVMs) to calculate valuations for the properties and to determine a valuation for the development based at least partly on the AVM valuations. In some implementations, the systems and methods can forecast market demand for the properties and generate a sales timeline for projected sales of the properties; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Examiner notes that Bleakly discloses “dynamic performance tracking” since it can take into consideration current market data to generate a plan/timeline):
a memory; and a processor coupled to the memory, the processor configured to perform the steps of (Paragraph 0064, The operations of a method or algorithm disclosed herein may be implemented in a processor-executable software module which may reside on a computer-readable medium. By way of example, and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, flash memory, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer): …;
receiving, at a first node of a network, home status data for the set of home builder communities, wherein a home builder community of the set of home builder communities comprises a respective set of homes, and wherein the home status data comprises at least a completion status for homes of the set of home builder communities, a set of historical performance data for the set of home builder communities, and a target metric (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0046, Certain implementations of the system 100 can forecast market demand for the virtual properties, determine a sales timeline for projected property sales in the development, and provide projected property valuations based on the sales timeline. The projected valuation for the development (or individual properties within the development) over time can be calculated based on the sales timeline. Certain such implementations use the forecasting module 130 to perform the forecasts and projections. For example, the forecasting module 130 can calculate average market demand using price points for the virtual properties and determine the sales timeline based at least partly on the forecast market demand and price points. The forecasting module 100 can accommodate situations in which the properties are developed in phases, for example, a first group of properties constructed and sold in phase 1, a second group of properties constructed and sold in phase 2 (which may, but need not be, at a later date than phase 1), and so forth; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Applicant defines “node” as one or more communication interfaces of the one or more networks, see Paragraph 0048 of Applicant’s specification. Based on broadest reasonable interpretation in light of the specification, Bleakley et al. discloses a first node of a network since it includes a network that is used to receive home status data. It can be noted that the claim language is written in alternative form. The limitation taught by Bleakly et al. is based on at least “a set of historical performance data for the set of home builder communities”);
determining a set of target paces associated with the set of home builder communities based on the home status data, where a target pace of the set of target paces is associated with completed home transactions for homes within a respective home builder community during a selected time period (Paragraph 0048, FIG. 3 shows an example of a market demand and sales timeline report 300 for a real estate development. The report 300 can be provided by the reporting module 136. In this example, the real estate development includes 217 residential properties that are sold in four plans or phases 302a-302d. The forecasting module 130 can estimate price changes for the properties over time (columns 320a, 320b, and 320c) to determine price points for future sales. Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner interprets the projected sales timeline as the set of target paces);
receiving, at the first node of the network, performance data associated with the set of home builder communities, wherein the performance data indicates historic home transactions associated with the set of home builder communities (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete);
extracting a plurality of features from the home status data and the performance data …; providing the set of feature … as input to the … model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, output …, and (ii) a predicted change in home transactions output … (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0048, Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time);
comparing the set of target paces to the performance data to determine a respective performance metric for the home builder community of the set of home builder communities (Paragraph 0047, The forecasting module 130 can access such information from the property valuation data stores 108a, 108b. Thus, in certain implementations, the system 100 can perform a market analysis based on such factors to determine the current characteristics of the real estate market in the area of the development. For example, the forecasting module 130 can analyze price differences between similar comparable properties as one possible indicator of market conditions. If similar properties are selling for very different prices, a volatile market may be indicated. Large percentages of distressed and REO sales may also be an indicator of a volatile market. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0048, FIG. 3 shows an example of a market demand and sales timeline report 300 for a real estate development. The report 300 can be provided by the reporting module 136. In this example, the real estate development includes 217 residential properties that are sold in four plans or phases 302a-302d. The forecasting module 130 can estimate price changes for the properties over time (columns 320a, 320b, and 320c) to determine price points for future sales. Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner notes that Bleakley et al. can compare the projected sales timeline with the recent sales to determine whether the current market is slow or fast);
and transmitting, to a second node of the network, a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction (Figure 1, item 116, Network; Paragraph 0022, One or more computing devices 112 can communicate with the valuation system 100 over the network 116. A user of the system 100 can use one of the computing devices 112 to request or access valuation information from the system 100. The computing devices 112 can include general purpose computers, data input devices (e.g., terminals or displays), web interfaces, portable or mobile computers, laptops or tablets, smart phones, etc.; Paragraph 0057, The information received and estimates performed at blocks 610-640 can be used at block 650 to determine the market demand and sales timeline for the properties. For example, the method 600 can determine the total time for completion of the real estate development (e.g., the time to sell all the properties) and a breakout of forecasted sales of the properties (e.g., sales per month or quarter; see example sales timeline in FIG. 3). The sales timeline can include estimated sales prices for the properties (e.g., as determined by AVM(s)) as well as upper or lower bounds on the estimated sales prices. The market demand and sales timeline can be used by a real estate developer to determine whether to purchase the underlying land to make the development and to determine profitable exit strategies. The market demand and sales timeline can be used by a lender to determine whether to finance the developer, and if so, by how much; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner interprets the “development plan in Fig. 3” as the “set of instructions” since it’s providing to the user a recommended plan based on historical performance metrics (e.g., sales of comparable properties)), wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: [recommending/estimating] a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities (Paragraph 0057, The sales timeline can include estimated sales prices for the properties (e.g., as determined by AVM(s)) as well as upper or lower bounds on the estimated sales prices. The market demand and sales timeline can be used by a real estate developer to determine whether to purchase the underlying land to make the development and to determine profitable exit strategies. The market demand and sales timeline can be used by a lender to determine whether to finance the developer, and if so, by how much; It can be noted that the claim language is written in alternative form. The limitation taught by Bleakley et al. is based on recommending/estimating a price).
Although Bleakley et al. discloses a predicted number of home transactions for the set of home builder communities for an upcoming time period (see Bleakley et al., Paragraph 0046, projected sales timeline; Paragraph 0057, estimated sales prices for the properties), Bleakley et al. does not specifically disclose wherein a machine learning is used for generating a predicted number of home transactions for the set of home builder communities for an upcoming time period.
However, Lin et al. discloses training, by the processor, a machine learning model comprising a recurrent neural network having a plurality of initial layers and a plurality of output layers on historical home transaction data and historical home demand data associated with a set of home builder communities, wherein training the machine learning model comprises applying an optimization algorithm to a training dataset comprising the historical home transaction data and the historical home demand data in a first training phase and a second training phase, and wherein the plurality of initial layers are shared across the plurality of output layers (Paragraph 0021, The one or more machine learning models can include supervised learning models, unsupervised learning models, semi-supervised learning models, and/or reinforcement learning models; Paragraph 0022, In various implementations, the one or more machine learning models can be trained on training data or a training set (discussed in more detail below). The training data or training set can be created by generating pairs of features (e.g., feature vectors) and/or ground-truth labels/values based on any of the data stored in databases 215 and 225. During training, the machine learning models can be adjusted or modified to fit the models to the training data by, e.g., adjusting or modifying model parameters, such as weights and/or biases, so as to minimize some error measure (e.g., a difference between a predicted value and an actual/ground-truth value) over the training data. The error measure can be evaluated using one or more loss functions; Paragraph 0025, FIG. 3 is a flow diagram illustrating a process of generating training data for one or more machine learning models, in accordance with some implementations of the present technology. At act 302, process 300 may obtain a set of real estate listings. The set of real estate listings can include information of real estate properties that are (i) currently available or (ii) currently unavailable for sale. For example, the real estate listings can be records of real estate properties (e.g., historical real estate records, real estate information based on census information, etc.), currently listed real estate listings (e.g., based on real estate listings available on one or more websites or databases), user uploaded real estate listing information, or other real estate listing related information. Each real estate listing of the set of real estate listings can be associated with a first geographic region. As an example, the first geographic region is a city block, a town, a county, a city, a state, a country, a continent, or other geographic region. Each real estate listing of the set of real estate listings may be associated with the same geographic region. For example, to generate accurate training data for a machine learning model (e.g., generate a selling soon prediction), real estate market's may vary region to region; Paragraph 0045, In some implementations, the machine learning models can include one or more neural networks or other machine learning models. In some implementations, neural networks may include multiple layers (e.g., where a signal path traverses from front layers to back layers); Paragraph 0047, In a recurrent structure, a node of a layer can be again input to the same node or layer at a subsequent time, while in a bi-directional structure, forward and backward connections may be provided; Examiner interprets the “historical real estate records for a first geographic region” as the “historical home transaction data and historical home demand data associated with a set of home builder communities”); …;
extracting a plurality of features from the home status data and the performance data to generate a set of feature vectors comprising a numerical representation of the plurality of features (Paragraph 0022, The training data or training set can be created by generating pairs of features (e.g., feature vectors) and/or ground-truth labels/values based on any of the data stored in databases 215 and 225; Paragraph 0037, Real estate listings may have one or more attributes changed over the time at which they are listed to the current time/date. For example, a given real estate listing may be updated with a more competitive price if the original price did not gain enough attention. As another example, a given real estate listing may sell (or go pending, under contract, or otherwise become unavailable) and may be re-listed. Such real estate listings may therefore have a higher days-sold value (e.g., as the original days-sold value may be added to the days-sold value one the listing was re-priced, re-listed, or other attribute was updated/changed). Therefore, as a real estate listing attribute may be updated, the days-sold value can be updated to reflect any change to ensure the system has the most accurate training data);
providing the set of feature vectors as input to the trained machine learning model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, output by a first output layer of the plurality of output layers, and (ii) a predicted change in home transactions output as a probability distribution over increase, decrease, and no-change outcomes by a second output layer of the plurality of output layers (Paragraph 0044, At act 306, process 300 can train a machine learning model based on training data. For example, as explained above, a machine learning model may be trained based on training data. In particular, process 300 uses the labeled set of real estate listings (e.g., as labeled in act 304) as training data for the machine learning model. For example, process 300 may train a machine learning model based on (or using) the labeled set of real estate listings. The machine learning model may be any machine learning model configured for generating selling soon predictions. The selling soon predictions can be related to (i) whether a given real estate listing will sell soon, (ii) how many days (or other time-related value) will a given real estate listing sell, (iii) probability related to whether a given real estate listing will sell faster than a percentage (or quantile, or other value corresponding to a quantile) of real estate listings within a given geographic region, or (iv) other prediction related to the selling (or unavailability) of a real estate listing; Paragraph 0047, As an example, where the machine learning models include a neural network, the neural network can include one or more input layers, hidden layers, and output layers; Examiner interprets the “probability of selling faster/slower” as the “probability of increase, decrease, and no-change”).
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for predicting a number of home transactions for the set of home builder communities for an upcoming time period (e.g., projected sales timeline for a real estate development project) of the invention of Bleakley et al. to further incorporate wherein a machine learning is used for generating the predictions of the invention of Lin et al. because doing so would allow the system to use the machine learning model for determining (i) whether a real estate listing will sell soon, (ii) how many days until the real estate listing will sell, or (iii) a probability indicating how fast the real estate listing will sell with respect to other real estate listings in a given geographic region (see Lin et al., Paragraph 0044). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Although Bleakley et al. discloses providing recommendations of a price of one or more homes within the one or more home builder communities (see Bleakley et al., Paragraph 0046, projected sales timeline; Paragraph 0057, estimated sales prices for the properties), the combination of Bleakley et al. and Lin et al. does not specifically disclose wherein the price is automatically adjusted.
However, Takamatsu et al. discloses and transmitting, to a second node of the network, a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction, wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: adjusting a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities (Paragraph 0128, The action may include adjusting a price of a property including the one or more features. Other insights are also or instead possible. For example, user activity may be evaluated in view of a property that is eventually purchased by a user, and/or in view of one or more properties that a user considered, ignored, viewed, otherwise engaged with, etc. That is, in certain aspects, the search criteria (and/or subsets thereof, such as the primary and secondary criteria discussed herein) may be compared to property attributes in the property profile of the listing that a user engaged with—e.g., purchased and/or viewed—and/or chose not to engage with. This analysis can be helpful to, e.g., adjust how the weighting is performed, adjust one or more buffer thresholds assigned to search criteria, adjust scoring and/or ranking, adjust displays, adjust property profiles, adjust marketing touches and techniques, take other actions, and so forth. That is, such an analysis may be used to adjust the relative importance of certain attributes/criteria for a user, which in turn can be used for similar users (e.g., users having similar demographics and/or budget, users in similar areas, users with similar wants/needs, and the like) and/or similar properties. Such an analysis may also or instead be used to identify trends in the relative importance and/or popularity (or lack thereof) of certain property attributes. And in turn, actions such as adjusting property descriptions, prices, recommendations, scores, and the like may be performed in light of this analysis; Paragraph 0137, As shown in step 1412, the method 1400 may include taking an action related to the calculated demand for one or more features. By way of example, the action may include one or more of the following or similar: adjusting a price of a property including one or more features (and/or making a recommendation regarding a pricing adjustment, e.g., if it is determined through a calculated demand that a price listing should be higher or lower than a current price; this can also or instead include an investment analysis when a price is deemed to be too high or too low, and/or adjusting valuation calculations/potential price); It can be noted that the claim language is written in alternative form. The limitation taught by Takamatsu et al. is based on “adjusting a price and adjusting an advertisement effort").
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for predicting a number of home transactions for the set of home builder communities for an upcoming time period (e.g., projected sales timeline and price for a real estate development project) of the invention of Bleakley et al. and Lin et al. to further incorporate wherein the price is automatically adjusted based on one or more performance metrics of the invention of Takamatsu et al. because doing so would allow the system to adjust the price of a property based on a calculated demand (see Takamatsu et al., Paragraph 0137). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Regarding claim 8 (Currently Amended), Bleakley et al. discloses a method for dynamic performance tracking for home builders, the method comprising (Abstract, The systems and methods can use automated valuation models (AVMs) to calculate valuations for the properties and to determine a valuation for the development based at least partly on the AVM valuations. In some implementations, the systems and methods can forecast market demand for the properties and generate a sales timeline for projected sales of the properties; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Examiner notes that Bleakly discloses “dynamic performance tracking” since it can take into consideration current market data to generate a plan/timeline): …;
receiving, at a first node of a network, home status data for a set of home builder communities, wherein a home builder community of the set of home builder communities comprises a respective set of homes, and wherein the home status data comprises at least a completion status for homes of the set of home builder communities, a set of historical performance data for the set of home builder communities, and a target metric (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0046, Certain implementations of the system 100 can forecast market demand for the virtual properties, determine a sales timeline for projected property sales in the development, and provide projected property valuations based on the sales timeline. The projected valuation for the development (or individual properties within the development) over time can be calculated based on the sales timeline. Certain such implementations use the forecasting module 130 to perform the forecasts and projections. For example, the forecasting module 130 can calculate average market demand using price points for the virtual properties and determine the sales timeline based at least partly on the forecast market demand and price points. The forecasting module 100 can accommodate situations in which the properties are developed in phases, for example, a first group of properties constructed and sold in phase 1, a second group of properties constructed and sold in phase 2 (which may, but need not be, at a later date than phase 1), and so forth; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Applicant defines “node” as one or more communication interfaces of the one or more networks, see Paragraph 0048 of Applicant’s specification. Based on broadest reasonable interpretation in light of the specification, Bleakley et al. discloses a first node of a network since it includes a network that is used to receive home status data. It can be noted that the claim language is written in alternative form. The limitation taught by Bleakly et al. is based on at least “a set of historical performance data for the set of home builder communities”);
determining a set of target paces associated with the set of home builder communities based on the home status data, where a target pace of the set of target paces is associated with completed home transactions for homes within a respective home builder community during a selected time period (Paragraph 0048, FIG. 3 shows an example of a market demand and sales timeline report 300 for a real estate development. The report 300 can be provided by the reporting module 136. In this example, the real estate development includes 217 residential properties that are sold in four plans or phases 302a-302d. The forecasting module 130 can estimate price changes for the properties over time (columns 320a, 320b, and 320c) to determine price points for future sales. Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner interprets the projected sales timeline as the set of target paces);
receiving, at the first node of the network, performance data associated with the set of home builder communities, wherein the performance data indicates historic home transactions associated with the set of home builder communities (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete);
extracting a plurality of features from the home status data and the performance data …; providing the set of feature … as input to the … model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, output …, and (ii) a predicted change in home transactions output … (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0048, Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time);
comparing the set of target paces to the performance data to determine a respective performance metric for the home builder community of the set of home builder communities (Paragraph 0047, The forecasting module 130 can access such information from the property valuation data stores 108a, 108b. Thus, in certain implementations, the system 100 can perform a market analysis based on such factors to determine the current characteristics of the real estate market in the area of the development. For example, the forecasting module 130 can analyze price differences between similar comparable properties as one possible indicator of market conditions. If similar properties are selling for very different prices, a volatile market may be indicated. Large percentages of distressed and REO sales may also be an indicator of a volatile market. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0048, FIG. 3 shows an example of a market demand and sales timeline report 300 for a real estate development. The report 300 can be provided by the reporting module 136. In this example, the real estate development includes 217 residential properties that are sold in four plans or phases 302a-302d. The forecasting module 130 can estimate price changes for the properties over time (columns 320a, 320b, and 320c) to determine price points for future sales. Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner notes that Bleakley et al. can compare the projected sales timeline with the recent sales to determine whether the current market is slow or fast);
transmitting, to a second node of the network, a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction (Figure 1, item 116, Network; Paragraph 0022, One or more computing devices 112 can communicate with the valuation system 100 over the network 116. A user of the system 100 can use one of the computing devices 112 to request or access valuation information from the system 100. The computing devices 112 can include general purpose computers, data input devices (e.g., terminals or displays), web interfaces, portable or mobile computers, laptops or tablets, smart phones, etc.; Paragraph 0057, The information received and estimates performed at blocks 610-640 can be used at block 650 to determine the market demand and sales timeline for the properties. For example, the method 600 can determine the total time for completion of the real estate development (e.g., the time to sell all the properties) and a breakout of forecasted sales of the properties (e.g., sales per month or quarter; see example sales timeline in FIG. 3). The sales timeline can include estimated sales prices for the properties (e.g., as determined by AVM(s)) as well as upper or lower bounds on the estimated sales prices. The market demand and sales timeline can be used by a real estate developer to determine whether to purchase the underlying land to make the development and to determine profitable exit strategies. The market demand and sales timeline can be used by a lender to determine whether to finance the developer, and if so, by how much; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner interprets the “development plan in Fig. 3” as the “set of instructions” since it’s providing the user a recommended plan based on historical performance metrics (e.g., sales of comparable properties)), wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: [recommending/estimating] a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities (Paragraph 0057, The sales timeline can include estimated sales prices for the properties (e.g., as determined by AVM(s)) as well as upper or lower bounds on the estimated sales prices. The market demand and sales timeline can be used by a real estate developer to determine whether to purchase the underlying land to make the development and to determine profitable exit strategies. The market demand and sales timeline can be used by a lender to determine whether to finance the developer, and if so, by how much; It can be noted that the claim language is written in alternative form. The limitation taught by Bleakley et al. is based on recommending/estimating a price).
Although Bleakley et al. discloses a predicted number of home transactions for the set of home builder communities for an upcoming time period (see Bleakley et al., Paragraph 0046, projected sales timeline; Paragraph 0057, estimated sales prices for the properties), Bleakley et al. does not specifically disclose wherein a machine learning is used for generating a predicted number of home transactions for the set of home builder communities for an upcoming time period.
However, Lin et al. discloses training a machine learning model comprising a recurrent neural network having a plurality of initial layers and a plurality of output layers on historical home transaction data and historical home demand data associated with a set of home builder communities, wherein training the machine learning model comprises applying an optimization algorithm to a training dataset comprising the historical home transaction data and the historical home demand data in a first training phase and a second training phase, and wherein the plurality of initial layers are shared across the plurality of output layers (Paragraph 0021, The one or more machine learning models can include supervised learning models, unsupervised learning models, semi-supervised learning models, and/or reinforcement learning models; Paragraph 0022, In various implementations, the one or more machine learning models can be trained on training data or a training set (discussed in more detail below). The training data or training set can be created by generating pairs of features (e.g., feature vectors) and/or ground-truth labels/values based on any of the data stored in databases 215 and 225. During training, the machine learning models can be adjusted or modified to fit the models to the training data by, e.g., adjusting or modifying model parameters, such as weights and/or biases, so as to minimize some error measure (e.g., a difference between a predicted value and an actual/ground-truth value) over the training data. The error measure can be evaluated using one or more loss functions; Paragraph 0025, FIG. 3 is a flow diagram illustrating a process of generating training data for one or more machine learning models, in accordance with some implementations of the present technology. At act 302, process 300 may obtain a set of real estate listings. The set of real estate listings can include information of real estate properties that are (i) currently available or (ii) currently unavailable for sale. For example, the real estate listings can be records of real estate properties (e.g., historical real estate records, real estate information based on census information, etc.), currently listed real estate listings (e.g., based on real estate listings available on one or more websites or databases), user uploaded real estate listing information, or other real estate listing related information. Each real estate listing of the set of real estate listings can be associated with a first geographic region. As an example, the first geographic region is a city block, a town, a county, a city, a state, a country, a continent, or other geographic region. Each real estate listing of the set of real estate listings may be associated with the same geographic region. For example, to generate accurate training data for a machine learning model (e.g., generate a selling soon prediction), real estate market's may vary region to region; Paragraph 0045, In some implementations, the machine learning models can include one or more neural networks or other machine learning models. In some implementations, neural networks may include multiple layers (e.g., where a signal path traverses from front layers to back layers); Paragraph 0047, In a recurrent structure, a node of a layer can be again input to the same node or layer at a subsequent time, while in a bi-directional structure, forward and backward connections may be provided; Examiner interprets the “historical real estate records for a first geographic region” as the “historical home transaction data and historical home demand data associated with a set of home builder communities”); …;
extracting a plurality of features from the home status data and the performance data to generate a set of feature vectors comprising a numerical representation of the plurality of features (Paragraph 0022, The training data or training set can be created by generating pairs of features (e.g., feature vectors) and/or ground-truth labels/values based on any of the data stored in databases 215 and 225; Paragraph 0037, Real estate listings may have one or more attributes changed over the time at which they are listed to the current time/date. For example, a given real estate listing may be updated with a more competitive price if the original price did not gain enough attention. As another example, a given real estate listing may sell (or go pending, under contract, or otherwise become unavailable) and may be re-listed. Such real estate listings may therefore have a higher days-sold value (e.g., as the original days-sold value may be added to the days-sold value one the listing was re-priced, re-listed, or other attribute was updated/changed). Therefore, as a real estate listing attribute may be updated, the days-sold value can be updated to reflect any change to ensure the system has the most accurate training data);
providing the set of feature vectors as input to the trained machine learning model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, output by a first output layer of the plurality of output layers, and (ii) a predicted change in home transactions output as a probability distribution over increase, decrease, and no-change outcomes by a second output layer of the plurality of output layers (Paragraph 0044, At act 306, process 300 can train a machine learning model based on training data. For example, as explained above, a machine learning model may be trained based on training data. In particular, process 300 uses the labeled set of real estate listings (e.g., as labeled in act 304) as training data for the machine learning model. For example, process 300 may train a machine learning model based on (or using) the labeled set of real estate listings. The machine learning model may be any machine learning model configured for generating selling soon predictions. The selling soon predictions can be related to (i) whether a given real estate listing will sell soon, (ii) how many days (or other time-related value) will a given real estate listing sell, (iii) probability related to whether a given real estate listing will sell faster than a percentage (or quantile, or other value corresponding to a quantile) of real estate listings within a given geographic region, or (iv) other prediction related to the selling (or unavailability) of a real estate listing; Paragraph 0047, As an example, where the machine learning models include a neural network, the neural network can include one or more input layers, hidden layers, and output layers; Examiner interprets the “probability of selling faster/slower” as the “probability of increase, decrease, and no-change”).
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for predicting a number of home transactions for the set of home builder communities for an upcoming time period (e.g., projected sales timeline for a real estate development project) of the invention of Bleakley et al. to further incorporate wherein a machine learning is used for generating the predictions of the invention of Lin et al. because doing so would allow the system to use the machine learning model for determining (i) whether a real estate listing will sell soon, (ii) how many days until the real estate listing will sell, or (iii) a probability indicating how fast the real estate listing will sell with respect to other real estate listings in a given geographic region (see Lin et al., Paragraph 0044). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Although Bleakley et al. discloses providing recommendations of a price of one or more homes within the one or more home builder communities (see Bleakley et al., Paragraph 0046, projected sales timeline; Paragraph 0057, estimated sales prices for the properties), the combination of Bleakley et al. and Lin et al. does not specifically disclose wherein the price is automatically adjusted.
However, Takamatsu et al. discloses transmitting, to a second node of the network, a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction, wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: adjusting a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities (Paragraph 0128, The action may include adjusting a price of a property including the one or more features. Other insights are also or instead possible. For example, user activity may be evaluated in view of a property that is eventually purchased by a user, and/or in view of one or more properties that a user considered, ignored, viewed, otherwise engaged with, etc. That is, in certain aspects, the search criteria (and/or subsets thereof, such as the primary and secondary criteria discussed herein) may be compared to property attributes in the property profile of the listing that a user engaged with—e.g., purchased and/or viewed—and/or chose not to engage with. This analysis can be helpful to, e.g., adjust how the weighting is performed, adjust one or more buffer thresholds assigned to search criteria, adjust scoring and/or ranking, adjust displays, adjust property profiles, adjust marketing touches and techniques, take other actions, and so forth. That is, such an analysis may be used to adjust the relative importance of certain attributes/criteria for a user, which in turn can be used for similar users (e.g., users having similar demographics and/or budget, users in similar areas, users with similar wants/needs, and the like) and/or similar properties. Such an analysis may also or instead be used to identify trends in the relative importance and/or popularity (or lack thereof) of certain property attributes. And in turn, actions such as adjusting property descriptions, prices, recommendations, scores, and the like may be performed in light of this analysis; Paragraph 0137, As shown in step 1412, the method 1400 may include taking an action related to the calculated demand for one or more features. By way of example, the action may include one or more of the following or similar: adjusting a price of a property including one or more features (and/or making a recommendation regarding a pricing adjustment, e.g., if it is determined through a calculated demand that a price listing should be higher or lower than a current price; this can also or instead include an investment analysis when a price is deemed to be too high or too low, and/or adjusting valuation calculations/potential price); It can be noted that the claim language is written in alternative form. The limitation taught by Takamatsu et al. is based on “adjusting a price and adjusting an advertisement effort").
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for predicting a number of home transactions for the set of home builder communities for an upcoming time period (e.g., projected sales timeline and price for a real estate development project) of the invention of Bleakley et al. and Lin et al. to further incorporate wherein the price is automatically adjusted based on one or more performance metrics of the invention of Takamatsu et al. because doing so would allow the system to adjust the price of a property based on a calculated demand (see Takamatsu et al., Paragraph 0137). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Regarding claim 15 (Currently Amended), Bleakley et al. discloses a computer program product for dynamic performance tracking for home builders, the computer program product comprising (Abstract, The systems and methods can use automated valuation models (AVMs) to calculate valuations for the properties and to determine a valuation for the development based at least partly on the AVM valuations. In some implementations, the systems and methods can forecast market demand for the properties and generate a sales timeline for projected sales of the properties; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0063, Implementations of the subject matter described in this specification also can be implemented as one or more computer programs, e.g., one or more modules of computer program instructions, encoded on a computer storage media for execution by, or to control the operation of data processing apparatus; Examiner notes that Bleakly discloses “dynamic performance tracking” since it can take into consideration current market data to generate a plan/timeline): …;
receiving, at a first node of a network, home status data for a set of home builder communities, wherein a home builder community of the set of home builder communities comprises a respective set of homes, and wherein the home status data comprises at least a completion status for homes of the set of home builder communities, a set of historical performance data for the set of home builder communities, and a target metric (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0046, Certain implementations of the system 100 can forecast market demand for the virtual properties, determine a sales timeline for projected property sales in the development, and provide projected property valuations based on the sales timeline. The projected valuation for the development (or individual properties within the development) over time can be calculated based on the sales timeline. Certain such implementations use the forecasting module 130 to perform the forecasts and projections. For example, the forecasting module 130 can calculate average market demand using price points for the virtual properties and determine the sales timeline based at least partly on the forecast market demand and price points. The forecasting module 100 can accommodate situations in which the properties are developed in phases, for example, a first group of properties constructed and sold in phase 1, a second group of properties constructed and sold in phase 2 (which may, but need not be, at a later date than phase 1), and so forth; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Applicant defines “node” as one or more communication interfaces of the one or more networks, see Paragraph 0048 of Applicant’s specification. Based on broadest reasonable interpretation in light of the specification, Bleakley et al. discloses a first node of a network since it includes a network that is used to receive home status data. It can be noted that the claim language is written in alternative form. The limitation taught by Bleakly et al. is based on at least “a set of historical performance data for the set of home builder communities”);
determining a set of target paces associated with the set of home builder communities based on the home status data, where a target pace of the set of target paces is associated with completed home transactions for homes within a respective home builder community during a selected time period (Paragraph 0048, FIG. 3 shows an example of a market demand and sales timeline report 300 for a real estate development. The report 300 can be provided by the reporting module 136. In this example, the real estate development includes 217 residential properties that are sold in four plans or phases 302a-302d. The forecasting module 130 can estimate price changes for the properties over time (columns 320a, 320b, and 320c) to determine price points for future sales. Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner interprets the projected sales timeline as the set of target paces);
receiving, at the first node of the network, performance data associated with the set of home builder communities, wherein the performance data indicates historic home transactions associated with the set of home builder communities (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete);
extracting a plurality of features from the home status data and the performance data …; providing the set of feature … as input to the … model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, output …, and (ii) a predicted change in home transactions output … (Figure 1, item 116, Network; Paragraph 0021, Some of the data stores can be local to the valuation system 104 (e.g., the data store 108a) and other data stores may be remotely connected to the system 104 through a network 116 (e.g., the data store 108b). For example, the valuation system 104 may access property valuation data from third-party data providers via the network 116; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0048, Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time);
comparing the set of target paces to the performance data to determine a respective performance metric for the home builder community of the set of home builder communities (Paragraph 0047, The forecasting module 130 can access such information from the property valuation data stores 108a, 108b. Thus, in certain implementations, the system 100 can perform a market analysis based on such factors to determine the current characteristics of the real estate market in the area of the development. For example, the forecasting module 130 can analyze price differences between similar comparable properties as one possible indicator of market conditions. If similar properties are selling for very different prices, a volatile market may be indicated. Large percentages of distressed and REO sales may also be an indicator of a volatile market. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; Paragraph 0048, FIG. 3 shows an example of a market demand and sales timeline report 300 for a real estate development. The report 300 can be provided by the reporting module 136. In this example, the real estate development includes 217 residential properties that are sold in four plans or phases 302a-302d. The forecasting module 130 can estimate price changes for the properties over time (columns 320a, 320b, and 320c) to determine price points for future sales. Based at least partly on the project market demand and price points for each type of property, the forecasting module 130 can calculate a sales timeline showing the number of sales of each type of property over time; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner notes that Bleakley et al. can compare the projected sales timeline with the recent sales to determine whether the current market is slow or fast);
transmitting, to a second node of the network, a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction (Figure 1, item 116, Network; Paragraph 0022, One or more computing devices 112 can communicate with the valuation system 100 over the network 116. A user of the system 100 can use one of the computing devices 112 to request or access valuation information from the system 100. The computing devices 112 can include general purpose computers, data input devices (e.g., terminals or displays), web interfaces, portable or mobile computers, laptops or tablets, smart phones, etc.; Paragraph 0057, The information received and estimates performed at blocks 610-640 can be used at block 650 to determine the market demand and sales timeline for the properties. For example, the method 600 can determine the total time for completion of the real estate development (e.g., the time to sell all the properties) and a breakout of forecasted sales of the properties (e.g., sales per month or quarter; see example sales timeline in FIG. 3). The sales timeline can include estimated sales prices for the properties (e.g., as determined by AVM(s)) as well as upper or lower bounds on the estimated sales prices. The market demand and sales timeline can be used by a real estate developer to determine whether to purchase the underlying land to make the development and to determine profitable exit strategies. The market demand and sales timeline can be used by a lender to determine whether to finance the developer, and if so, by how much; Paragraph 0058, The method 600 (or the developer) can analyze the results for each development plan to determine which plan most closely meets (or exceeds) the developer's goal for the development; Examiner interprets the “development plan in Fig. 3” as the “set of instructions” since it’s providing the user a recommended plan based on historical performance metrics (e.g., sales of comparable properties)), wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: [recommending/estimating] a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities (Paragraph 0057, The sales timeline can include estimated sales prices for the properties (e.g., as determined by AVM(s)) as well as upper or lower bounds on the estimated sales prices. The market demand and sales timeline can be used by a real estate developer to determine whether to purchase the underlying land to make the development and to determine profitable exit strategies. The market demand and sales timeline can be used by a lender to determine whether to finance the developer, and if so, by how much; It can be noted that the claim language is written in alternative form. The limitation taught by Bleakley et al. is based on recommending/estimating a price).
Although Bleakley et al. discloses a predicted number of home transactions for the set of home builder communities for an upcoming time period (see Bleakley et al., Paragraph 0046, projected sales timeline; Paragraph 0057, estimated sales prices for the properties), Bleakley et al. does not specifically disclose wherein a machine learning is used for generating a predicted number of home transactions for the set of home builder communities for an upcoming time period.
However, Lin et al. discloses training a machine learning model comprising a recurrent neural network having a plurality of initial layers and a plurality of output layers on historical home transaction data and historical home demand data associated with a set of home builder communities, wherein training the machine learning model comprises applying an optimization algorithm to a training dataset comprising the historical home transaction data and the historical home demand data in a first training phase and a second training phase, and wherein the plurality of initial layers are shared across the plurality of output layers (Paragraph 0021, The one or more machine learning models can include supervised learning models, unsupervised learning models, semi-supervised learning models, and/or reinforcement learning models; Paragraph 0022, In various implementations, the one or more machine learning models can be trained on training data or a training set (discussed in more detail below). The training data or training set can be created by generating pairs of features (e.g., feature vectors) and/or ground-truth labels/values based on any of the data stored in databases 215 and 225. During training, the machine learning models can be adjusted or modified to fit the models to the training data by, e.g., adjusting or modifying model parameters, such as weights and/or biases, so as to minimize some error measure (e.g., a difference between a predicted value and an actual/ground-truth value) over the training data. The error measure can be evaluated using one or more loss functions; Paragraph 0025, FIG. 3 is a flow diagram illustrating a process of generating training data for one or more machine learning models, in accordance with some implementations of the present technology. At act 302, process 300 may obtain a set of real estate listings. The set of real estate listings can include information of real estate properties that are (i) currently available or (ii) currently unavailable for sale. For example, the real estate listings can be records of real estate properties (e.g., historical real estate records, real estate information based on census information, etc.), currently listed real estate listings (e.g., based on real estate listings available on one or more websites or databases), user uploaded real estate listing information, or other real estate listing related information. Each real estate listing of the set of real estate listings can be associated with a first geographic region. As an example, the first geographic region is a city block, a town, a county, a city, a state, a country, a continent, or other geographic region. Each real estate listing of the set of real estate listings may be associated with the same geographic region. For example, to generate accurate training data for a machine learning model (e.g., generate a selling soon prediction), real estate market's may vary region to region; Paragraph 0045, In some implementations, the machine learning models can include one or more neural networks or other machine learning models. In some implementations, neural networks may include multiple layers (e.g., where a signal path traverses from front layers to back layers); Paragraph 0047, In a recurrent structure, a node of a layer can be again input to the same node or layer at a subsequent time, while in a bi-directional structure, forward and backward connections may be provided; Examiner interprets the “historical real estate records for a first geographic region” as the “historical home transaction data and historical home demand data associated with a set of home builder communities”); …;
extracting a plurality of features from the home status data and the performance data to generate a set of feature vectors comprising a numerical representation of the plurality of features (Paragraph 0022, The training data or training set can be created by generating pairs of features (e.g., feature vectors) and/or ground-truth labels/values based on any of the data stored in databases 215 and 225; Paragraph 0037, Real estate listings may have one or more attributes changed over the time at which they are listed to the current time/date. For example, a given real estate listing may be updated with a more competitive price if the original price did not gain enough attention. As another example, a given real estate listing may sell (or go pending, under contract, or otherwise become unavailable) and may be re-listed. Such real estate listings may therefore have a higher days-sold value (e.g., as the original days-sold value may be added to the days-sold value one the listing was re-priced, re-listed, or other attribute was updated/changed). Therefore, as a real estate listing attribute may be updated, the days-sold value can be updated to reflect any change to ensure the system has the most accurate training data);
providing the set of feature vectors as input to the trained machine learning model to generate a performance prediction comprising (i) a predicted number of home transactions for the set of home builder communities for an upcoming time period, output by a first output layer of the plurality of output layers, and (ii) a predicted change in home transactions output as a probability distribution over increase, decrease, and no-change outcomes by a second output layer of the plurality of output layers (Paragraph 0044, At act 306, process 300 can train a machine learning model based on training data. For example, as explained above, a machine learning model may be trained based on training data. In particular, process 300 uses the labeled set of real estate listings (e.g., as labeled in act 304) as training data for the machine learning model. For example, process 300 may train a machine learning model based on (or using) the labeled set of real estate listings. The machine learning model may be any machine learning model configured for generating selling soon predictions. The selling soon predictions can be related to (i) whether a given real estate listing will sell soon, (ii) how many days (or other time-related value) will a given real estate listing sell, (iii) probability related to whether a given real estate listing will sell faster than a percentage (or quantile, or other value corresponding to a quantile) of real estate listings within a given geographic region, or (iv) other prediction related to the selling (or unavailability) of a real estate listing; Paragraph 0047, As an example, where the machine learning models include a neural network, the neural network can include one or more input layers, hidden layers, and output layers; Examiner interprets the “probability of selling faster/slower” as the “probability of increase, decrease, and no-change”).
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for predicting a number of home transactions for the set of home builder communities for an upcoming time period (e.g., projected sales timeline for a real estate development project) of the invention of Bleakley et al. to further incorporate wherein a machine learning is used for generating the predictions of the invention of Lin et al. because doing so would allow the system to use the machine learning model for determining (i) whether a real estate listing will sell soon, (ii) how many days until the real estate listing will sell, or (iii) a probability indicating how fast the real estate listing will sell with respect to other real estate listings in a given geographic region (see Lin et al., Paragraph 0044). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Although Bleakley et al. discloses providing recommendations of a price of one or more homes within the one or more home builder communities (see Bleakley et al., Paragraph 0046, projected sales timeline; Paragraph 0057, estimated sales prices for the properties), the combination of Bleakley et al. and Lin et al. does not specifically disclose wherein the price is automatically adjusted.
However, Takamatsu et al. discloses and transmitting, to a second node of the network, a set of instructions corresponding to one or more home builder communities of the set of home builder communities, the set of instructions based on one or more performance metrics associated with the one or more home builder communities and the performance prediction, wherein the set of instructions causes automatic execution of one or more remedial actions comprising at least one of: adjusting a price of one or more homes within the one or more home builder communities, adjusting an advertising effort for the one or more home builder communities, or adjusting a construction rate for homes within the one or more home builder communities (Paragraph 0128, The action may include adjusting a price of a property including the one or more features. Other insights are also or instead possible. For example, user activity may be evaluated in view of a property that is eventually purchased by a user, and/or in view of one or more properties that a user considered, ignored, viewed, otherwise engaged with, etc. That is, in certain aspects, the search criteria (and/or subsets thereof, such as the primary and secondary criteria discussed herein) may be compared to property attributes in the property profile of the listing that a user engaged with—e.g., purchased and/or viewed—and/or chose not to engage with. This analysis can be helpful to, e.g., adjust how the weighting is performed, adjust one or more buffer thresholds assigned to search criteria, adjust scoring and/or ranking, adjust displays, adjust property profiles, adjust marketing touches and techniques, take other actions, and so forth. That is, such an analysis may be used to adjust the relative importance of certain attributes/criteria for a user, which in turn can be used for similar users (e.g., users having similar demographics and/or budget, users in similar areas, users with similar wants/needs, and the like) and/or similar properties. Such an analysis may also or instead be used to identify trends in the relative importance and/or popularity (or lack thereof) of certain property attributes. And in turn, actions such as adjusting property descriptions, prices, recommendations, scores, and the like may be performed in light of this analysis; Paragraph 0137, As shown in step 1412, the method 1400 may include taking an action related to the calculated demand for one or more features. By way of example, the action may include one or more of the following or similar: adjusting a price of a property including one or more features (and/or making a recommendation regarding a pricing adjustment, e.g., if it is determined through a calculated demand that a price listing should be higher or lower than a current price; this can also or instead include an investment analysis when a price is deemed to be too high or too low, and/or adjusting valuation calculations/potential price); It can be noted that the claim language is written in alternative form. The limitation taught by Takamatsu et al. is based on “adjusting a price and adjusting an advertisement effort").
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for predicting a number of home transactions for the set of home builder communities for an upcoming time period (e.g., projected sales timeline and price for a real estate development project) of the invention of Bleakley et al. and Lin et al. to further incorporate wherein the price is automatically adjusted based on one or more performance metrics of the invention of Takamatsu et al. because doing so would allow the system to adjust the price of a property based on a calculated demand (see Takamatsu et al., Paragraph 0137). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Regarding claims 3, 10, and 17 (Currently Amended), which are dependent of claims 1, 8, and 15, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claims 1, 8, and 15. Bleakley et al. further discloses wherein being ahead of the target pace comprises having a historical performance metric of historical home transaction data more than 0.5 home transactions above the target pace, meeting the target pace comprises having a historical performance metric within 0.5 home transactions of the target pace, and being behind the target pace comprises having a historical performance metric more than 0.5 home transactions below than the target pace (Paragraph 0055, In this example, at block 610, the method 600 estimates monthly supply and average selling speed for homes in the geographic area of the development. The geographic area may be determined as having the same zip code as the development (or neighboring zip codes). MLS listing information on home supply, inventory, or demand, and sales closing data can be used. The method 600 may receive tolerances (e.g., +/-15%) in order to provide estimated upper or lower bounds on the supply and selling speed for homes. At block 620, the method 600 estimates market cycle trends in the area. For example, the method 600 can estimate appreciation or depreciation in values for the homes in the area. In some cases, the method 600 can use market indices such as HPI to forecast home price trends, market volatility, and elasticity in the area. At block 630, the method 600 can estimate equity percentage (or negative equity percentage) in the area).
Regarding claims 4, 11, and 18 (Previously Presented), which are dependent of claims 3, 10, and 17, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claims 3, 10, and 17. Bleakley et al. further discloses wherein the completion status for each home of the set of home builder communities indicates that a given home is scheduled to be built, within a first building phase, within a second building phase, or fully built (Paragraph 0046, Certain implementations of the system 100 can forecast market demand for the virtual properties, determine a sales timeline for projected property sales in the development, and provide projected property valuations based on the sales timeline. The projected valuation for the development (or individual properties within the development) over time can be calculated based on the sales timeline. Certain such implementations use the forecasting module 130 to perform the forecasts and projections. For example, the forecasting module 130 can calculate average market demand using price points for the virtual properties and determine the sales timeline based at least partly on the forecast market demand and price points. The forecasting module 100 can accommodate situations in which the properties are developed in phases, for example, a first group of properties constructed and sold in phase 1, a second group of properties constructed and sold in phase 2 (which may, but need not be, at a later date than phase 1), and so forth).
Regarding claims 5 and 12 (Previously Presented), which are dependent of claims 3 and 10, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claims 3 and 10. Bleakley et al. further discloses wherein the historical performance metric comprises an average historical performance over a period of time (Paragraph 0046, Certain such implementations use the forecasting module 130 to perform the forecasts and projections. For example, the forecasting module 130 can calculate average market demand using price points for the virtual properties and determine the sales timeline based at least partly on the forecast market demand and price points).
Regarding claims 6, 13, and 19 (Original), which are dependent of claims 1, 8, and 17, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claims 1, 8, and 17. Bleakley et al. further comprising receiving a user input that includes the selected time period (Paragraph 0036, For example, the search parameters can include distance from the property and how far back in time to search for relevant transactions. In some embodiments, an initial search is performed with relatively small distance or time parameters, and if too few relevant transactions are found, the extent of the search parameters can be increased and the search broadened until sufficient "comps" are found for an AVM valuation to be performed).
Regarding claims 7, 14, and 20 (Original), which are dependent of claims 1, 8, and 15, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claims 1, 8, and 15. Bleakley et al. further comprising performing at least one of the following steps: tracking the performance data for a home builder community and dynamically updating the respective target pace and performance metric for the home builder community based on the tracking; receiving additional home status data for new homes in a home builder community and dynamically updating the target pace and performance metric based on the additional home status data; receiving the home status data from a client device, a proprietary feed, a public data source, a first data source, or a combination thereof; receiving the performance data from a client device, a public performance data source or feed; a second data source, or a combination thereof; or outputting to the GUI a representation of the home status data (Paragraph 0028, Multiple listing service (MLS) listing information can be accessed to provide information on how long properties in the surrounding area have been for sale and changes to the asking price. MLS data may also include months of supply and market inventory. In some implementations, the system 100 can access MLS data (e.g., over the network 116) from services that use the Real Estate Transaction Standard (RETS), which provides a common standard for MLS data exchange between computing systems. The system 100 additionally or alternatively can access machine-readable versions of MLS information (or other information). For example, the machine-readable version can include an extensible markup language (XML) version of fields in MLS listings. Other information that can be used includes sales transaction history by price for properties in the surrounding area can be used, the share (or percentage) of properties with positive equity or negative equity, etc.; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete; It can be noted that the claim language is written in alternative form. The limitation taught by Bleakley et al. is based on “receiving the performance data from a second data source." In this case, Examiner interprets the “MLS data” as the “second data source”).
Regarding claim 21 (Previously Presented), which is dependent of claim 1, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claim 1. Bleakley et al. further discloses wherein the processor is further configured to present, at the GUI, one or more selectable elements which, upon receiving one or more user inputs, modifies data sources used for generating the set of historical performance data (Paragraph 0028, The virtual property characteristics can also include information on features of the development that can influence value. Examples of such features that tend to positively influence value are scenic views, golf courses, swimming pools, parks, schools, day care centers, presence of gates (manned or unmanned), etc. Examples of features that tend to negatively influence value are close proximity to highways, railroads, telephone lines or electrical power lines, poor performing schools, close proximity to high crime areas, etc. In some implementations, such data can be acquired via geospatial geographic information systems (GIS), via user input, or other data sources; Paragraph 0036, The valuation analyzer 128 (or an individual AVM) can access the property valuation data in data stores 108a or 108b to search for and identify properties in the geographic location that are similar to the virtual properties (e.g., have the same use code type) and which have recent sales transactions; Paragraph 0041, The system 100 can provide a graphical user interface (GUI) by which a user can access the system 100 (e.g., via a web browser or an application (e.g., app or widget) on a computing device 112) in order to input data or user requirements for the valuation and to receive or access the valuation report. In some implementations, the system 100 provides an application programming interface (API) by which software applications can be programmed to access the system 100 to input or retrieve data, property valuations, reports, etc; Paragraph 0056, Some embodiments of the method 600 can accommodate phased developments in which groups of properties may be constructed at different times (e.g., phase 1 in year 1, phase 2 in year 2, and so forth) or in different locations within the development (e.g., phase 1 at a north end, phase 2 at a south end, and so forth)).
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Bleakley et al. (US 2013/0346151 A1), in view of Lin et al. (US 2024/0070741 A1), in further view of Takamatsu et al. (US 2018/0082388 A1) and Hunt et al. (US 2008/0294996 A1).
Regarding claim 22 (Previously Presented), which is dependent of claim 1, the combination of Bleakley et al., Lin et al., and Takamatsu et al. discloses all the limitations in claim 1. Bleakley et al. further discloses wherein the processor is further configured to present, at the GUI and based on the home status data: a predicted increase graph representing a fourth subset of the set of home builder communities with a predicted increased performance …; a predicted decrease graph representing a fifth subset of the set of home builder communities with a predicted decreased performance …; and a predicted no change graph representing a sixth subset of the set of home builder communities with a predicted no change in performance … (Paragraph 0037, As discussed further below, some implementations of the system 100 can forecast market demand for properties in the development to provide a projected sales timeline and valuations for the development. Accordingly, the property valuation data can also include scores or metrics reflecting property values, sales demand, or sales propensity; Paragraph 0041, The system 100 can provide a graphical user interface (GUI) by which a user can access the system 100 (e.g., via a web browser or an application (e.g., app or widget) on a computing device 112) in order to input data or user requirements for the valuation and to receive or access the valuation report. In some implementations, the system 100 provides an application programming interface (API) by which software applications can be programmed to access the system 100 to input or retrieve data, property valuations, reports, etc.; Paragraph 0047, The forecasting module 130 can analyze a number of factors that can affect property selling propensity including the supply, inventory, and demand for properties and volatility of the property market in the area of the development, conformity of the development properties as compared to the surrounding area, and so forth. The forecasting module 130 can also analyze the number of recent sales in relation to the density of the area. If the current market is very slow, the property sales in the development may take a long to complete).
Bleakley et al. discloses outputting to a graphical user interface a sales plan (see Bleakley et al., Paragraph 0046, projected sales timeline) and performance metrics (see Bleakley et al., Paragraph 0047, recent sales data to determine whether the current market is slow or fast) for a subset of the set of home builder communities. Although Bleakley et al. discloses comparing the projected sales timeline with the recent sales to determine whether the current market is slow or fast (e.g., comparing projected sales to current sales to determine whether the market is improving or deteriorating), Bleakley et al. does not specifically disclose wherein the performance is compared to the previous time period.
However, Hunt et al. discloses wherein the processor is further configured to present, at the GUI and based on the [real estate] data: a predicted increase graph representing a fourth subset of [real estate] with a predicted increased performance compared to a previous time period; a predicted decrease graph representing a fifth subset of [real estate] with a predicted decreased performance compared to the previous time period; and a predicted no change graph representing a sixth subset of [real estate] with a predicted no change in performance compared to the previous time period (Paragraph 0276, Continuing to refer to FIG. 1, an interface 182 may be included in the analytic platform 100. In embodiments, data may be transferred to the MDMH 150 of the platform 100 using a user interface 182. The interface 182 may be a web browser operating over the Internet or within an intranet or other network, it may be an analytic server 134, an application plug-in, or some other user interface that is capable of handling data; Paragraph 0280, The analytic platform 100 may be applied to opportunities to vend large amounts of data through a portal with the possibility to deliver highly customized views for individual users with effectively controlled user accessibility rights. This may include collaborative groups such as insurance brokers, real estate agents, and the like; Paragraph 0324, New product performance solutions 188 may include new product planning, such as portfolio analysis, product hierarchies, product attribute trend analysis, new product metrics, track actual vs. plan, forecast current sales, identify and monitor innovation type attributes, predict sales volume, integrate promotion and media plans, or the like. New product performance solutions may also include launch management, such as tracking sales rate index, new product alerts, product success percentile and trending, tracking trial and repeat performance, sales variance drivers analysis, relative time launch-aligned view, rapid product placement process, tracking trial and repeat, or the like; Paragraph 0414, A company receives movement data that is automatically collected from point-of-sale machines that are installed at a group of census stores. The movement data may provide direct insight into what has sold. From that, it may be possible to infer some of the reasons as to why it sold. For example, suppose an item is selling better this week than it did last week. It might be clear from the movement data that the price of the product was reduced and that this seemed to drive sales. However, one might want to know whether this increase in sales may be associated with an in-store promotion, a re-positioning of the item on store shelves, or some other factor that may not be clear from the census data).
It would have been obvious to one ordinary skill in the art before the effective filing date to modify the system for dynamic performance tracking for home builders, wherein a GUI is used to display a set of instructions based on one or more performance metrics of a subset of the set of home builder communities (e.g., first subset associated with one phase, second subset associated with a second phase, and third subset associated with a third phase) of the invention of Bleakley et al. to further incorporate wherein the GUI further includes a representation of the performance metrics (e.g., an increase or decrease of performance compared to previous time period) of the invention of Hunt et al. because doing so would allow the GUI to provide highly customized views for individual users such as movement data, which allows a user to identify whether an item is selling better this week than it did last week (see Hunt et al., Paragraph 0414). Further, the claimed invention is merely a combination of old elements, and in combination each element would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
Smith (US 2016/0292800 A1) – discloses data extracted from multiple listing services (MLSs), county property sales data, and/or other databases tracking real estate sold property information and/or properties actively for sale (see at least Paragraph 0025).
Lush et al. (US 2020/0143402 A1) – discloses a change application 500 that facilitates determination if the subject property is not performing as expected. For example, if a house is being showed a lot, but no one is buying—why? If the house is having less showings than it should, perhaps it is priced too high (see at least Paragraph 0064).
Villena et al. (US 2006/0105342 A1) – discloses in step 510, the AVM database of step 506 can be further updated to reflect the new market value of other properties based on the sale price, an adjusted sale price (i.e., the sale price adjusted based on concessions made by the buyer or seller (or other value) that might better reflect the actual sale value of the property) and/or modified AVM value of the sold property. As discussed above, such properties to be updated may include only properties in a same development, properties within a same locality, properties within a certain distance from the sold property, properties having similar structural features, such as acreage, area, builder, number of bedrooms, etc. (see at least Paragraph 0088).
Zhao (Y. Zhao, G. Chetty and D. Tran, "Deep Learning for Real Estate Trading," 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), Gold Coast, Australia, 2022, pp. 1-7, doi: 10.1109/CSDE56538.2022.10089222) – discloses machine learning (ML) technology for providing support on real estate investment decisions, allows investigation of historical property sales data by computer algorithms to automatically predict house prices (see at least Abstract).
Reddy (US 2024/0386512 A1) – discloses making a recommendation regarding a pricing adjustment, e.g., if it is determined through a calculated demand that a price listing should be higher or lower than a current price; this can also or instead include an investment analysis when a price is deemed to be too high or too low, and/or adjusting valuation calculations/potential price (see at least Paragraph 0137).
Yang (US 20220129932 A1) – discloses to determine the price adjustment, the property system provides, as input to the newly trained machine-learned model, engagement data as described above in reference to FIG. 1, and the newly trained machine-learned model can output a state (price should be increased, decreased, or remain the same), an updated rental or purchase price, or a change to the rental or purchase price (see at least Paragraph 0033).
Urry et al. (US 2017/0300844 A1) - discloses to display visual cues related to a comparison of the target metric to the metric forecast. For example, in response to the metric forecast being equal to or less than the target metric, user interaction module 170 may display a first visual cue. For example, if the target metric comprised time to completion of 4 weeks, and the metric forecast comprised a time of completion of 3 weeks, user interaction module 170 may display the first visual cue. The first visual cue may be representative that the construction project is on pace for, or is under the originally forecasted metric (e.g., ahead of schedule). In response to the metric forecast being greater than the target metric, user interaction module 170 may display a second visual cue. For example, if the target metric comprised time to completion of 4 weeks, and the metric forecast comprised a time of completion of 5 weeks, user interaction module 170 may display the second visual cue. The second visual cue may therefore be representative that the construction project is currently exceeding the originally forecasted metric (e.g., behind schedule) (see at least Paragraph 0042).
Yu (CN 119941473 A) – discloses according to the time sequence of the project development, the simulation process starts from the land acquisition, gradually simulates the cost expenditure and project progress in the development and construction process, and the income inflow in the sales or rental operation stage after the project is completed, and calculates the financial condition and key index change of the project on each time node. For example, under the optimistic situation, because the house price is increased and the selling speed is accelerated, the selling income of the project will be realized in advance and the amount is increased, so the index such as profit, investment rate of return and so on will be quickly improved; Under the pessimistic situation, there may be difficulties in sales, and the return of capital is slow, resulting in increased cost pressure and worsening financial indicators (see at least Page 18, Scene simulation and analysis).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARJORIE PUJOLS-CRUZ whose telephone number is (571)272-4668. The examiner can normally be reached Mon-Thru 7:30 AM - 5:00 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Patricia H Munson can be reached at (571)270-5396. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MARJORIE PUJOLS-CRUZ/Examiner, Art Unit 3624
Prosecution Insights