Information processing device, information processing method, and information processing program

Abstract

To improve the liquidity of real estate existing in the world. [Solution] An information processing device that includes a calculation unit that inputs real estate information as input data and calculates the probability of a transaction for each real estate sales price for a transaction probability estimation model that estimates the probability of a real estate transaction, the model being generated by learning from past real estate transaction records as training data, and a generation unit that generates display data for displaying an image showing the change in the probability of a transaction due to differences in real estate sales prices.

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] In the above technical field, Patent Document 1 discloses a technique for determining the type of vacant house based on measurement history information of energy consumption and generating a vacant house rate map showing the vacant house rate for each predetermined area on a map. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-157634 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, although the technology described in the above document can recognize the existence of vacant houses, it does not provide any measures for circulating the vacant houses.

[0005] An object of the present invention is to provide a technique for solving the above-mentioned problems. [Means for solving the problem]

[0006] In order to achieve the above object, the device according to the present invention comprises: a calculation unit that inputs real estate information as input data into a transaction probability estimation model that estimates a transaction probability, the transaction probability estimation model being generated by learning from past transaction records of real estate as training data, and calculates a transaction probability for each real estate sales price; a generating unit that generates display data for displaying an image showing a change in the probability of closing a deal depending on the difference in the real estate selling price; Equipped with 、 The contract probability estimation model is generated by learning whether or not a contract has been concluded for each of the real estate properties and for each period from when the contract price was presented to when the person moved in, using the presence or absence of a contract as a target variable. It is an information processing device. In order to achieve the above object, another device according to the present invention comprises: a calculation unit that inputs real estate information as input data into a transaction probability estimation model that estimates a transaction probability, the transaction probability estimation model being generated by learning from past transaction records of real estate as training data, and calculates a transaction probability for each real estate sales price; a generating unit that generates display data for displaying an image showing a change in the probability of closing a deal depending on the difference in the real estate selling price; Equipped with The contract probability estimation model is an information processing device that is generated by learning at least the contract price and the period from when the contract price is presented until the person moves in for each of the real estate properties as objective variables. .

[0007] In order to achieve the above object, the method according to the present invention comprises: a calculation step in which the calculation unit inputs real estate information as input data into a transaction probability estimation model that estimates a transaction probability, the transaction probability estimation model being generated by learning from past transaction records of real estate as training data, and calculates a transaction probability for each real estate sales price; a generation step of generating display data for displaying an image showing a change in the probability of closing a deal depending on a difference in the real estate selling price by a generation unit; Including fruit, The contract probability estimation model is generated by learning whether or not a contract has been concluded for each of the real estate properties and for each period from when the contract price was presented to when the person moved in, using the presence or absence of a contract as a target variable. It is an information processing method.

[0008] In order to achieve the above object, the program according to the present invention comprises: a calculation step of inputting real estate information as input data into a transaction probability estimation model that estimates the probability of a transaction, the model being generated by learning from past transaction records of real estate as training data, and calculating the probability of a transaction for each real estate sales price; a generating step of generating display data for displaying an image showing a change in the probability of closing a deal depending on the difference in the real estate selling price; An information processing program that causes a computer to execute And, The contract probability estimation model is generated by learning whether or not a contract has been concluded for each of the real estate properties and for each period from when the contract price was presented to when the person moved in, using the presence or absence of a contract as a target variable. It is an information processing program. Effect of the Invention

[0009] According to the present invention, it is possible to improve the liquidity of real estate. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of an information processing device according to a first embodiment. [Diagram 2] FIG. 11 is a diagram showing a background of the information processing device according to the second embodiment. [Diagram 3] FIG. 11 is a diagram showing an overview of processing performed by an information processing device according to a second embodiment. [Figure 4A] FIG. 11 is a block diagram showing a functional configuration of an information processing device according to a second embodiment. [Figure 4B] FIG. 11 is a diagram illustrating a configuration of a teacher data storage unit according to the second embodiment. [Diagram 5] 10 is a flowchart showing a processing procedure of an information processing device according to a second embodiment. [Figure 6] FIG. 11 is a diagram showing a contract probability distribution according to the second embodiment. [Figure 7] FIG. 11 is a diagram showing prediction accuracy according to the second embodiment. [Figure 8] FIG. 11 is a diagram showing an example of a display screen according to the second embodiment. [Figure 9] FIG. 11 is a diagram showing an example of a display screen according to the second embodiment. [Figure 10] FIG. 11 is a block diagram showing a functional configuration of an information processing device according to a third embodiment. [Figure 11] FIG. 13 is a block diagram showing a functional configuration of an information processing device according to a fourth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. However, the components described in the following embodiment are merely examples, and are not intended to limit the technical scope of the present invention.

[0012] [First embodiment] An information processing device 100 according to a first embodiment of the present invention will be described with reference to Fig. 1. The information processing device 100 is a device for realizing a reduction in the vacant house period.

[0013] As shown in FIG. 1, the information processing device 100 includes a contract probability calculation unit 101 and a display data generation unit .

[0014] The closing probability calculation unit 101 inputs real estate information 120 as input data into a closing probability estimation model 111 that estimates the closing probability, which is generated by learning from past real estate closing records 110 as training data, and calculates the closing probability for each real estate sales price.

[0015] The display data generating unit 102 generates display data for displaying an image showing a change 130 in the probability of closing a deal due to differences in real estate sales prices.

[0016] According to the above configuration, it is possible to provide the user with information on changes in the probability of closing a deal due to differences in real estate sales prices according to real estate information, thereby improving the liquidity of real estate.

[0017] [Second embodiment] Next, an information processing device according to a second embodiment of the present invention will be described with reference to FIG. 2 and subsequent figures. FIG. 2 is a diagram for explaining the necessity of the information processing device according to this embodiment. As shown in FIG. 2, currently 201, there are many used houses that have no buyers and are called "negative assets". This is the result of the owner not being able to sell the vacant house at the desired price, and the damage has progressed during that time, making it even more difficult to sell. The selling price tends to be high because both the owner and the real estate agent will make more profit if they sell it at a high price, but if it cannot be sold for a year or two, the damage to the house will worsen and it will become even more difficult to sell. As the damage progresses, the owner's burden increases, so the local government and others consult with them, but in many cases, the damage has progressed by the time of consultation and there is no prospect of selling it. There is no other way than demolition. The local government also faces a heavy workload, such as responding to complaints from neighboring residents and dealing with repairs.

[0018] In the Ideal State 202, owners will understand how different sales prices will increase the probability of a deal, and will review the selling price of their property at an early stage, cooperate with real estate sales intermediaries, register their property on real estate sites early, set a fair price, make repairs, etc. By allowing owners to take early and accurate measures to market their property, it will be possible to shorten the vacant house period and promote and standardize the market for used homes.

[0019] <Overview of processing by information processing device> 3 is a diagram showing an overview of processing by the information processing device according to this embodiment. Data used by the information processing device is roughly divided into real estate advertisement data 301, lifeline data 302, basic resident register data 303, and open data 304.

[0020] First, it is detected that a person has moved into a property, that is, that a sale of the property has been concluded, using either or both of the lifeline data 302 and the basic resident register data 303. Even if only one of the lifeline data 302 and the basic resident register data 303 is available, it is possible to detect the conclusion of a sale. Contractor information / customer information may also be used.

[0021] Next, the real estate advertisement data 301 obtained from the real estate agency is used to estimate the contract price and advertising period of the property. The real estate advertisement data 301 is data on real estate sales advertisements submitted at the request of the user. This real estate sales advertisement data includes the history of the sales prices at which real estate owned by the user has been advertised. By looking at this real estate sales advertisement data, it is possible to know the advertised sales price immediately before a new tenant moves in. This sales price is estimated to be the contract price.

[0022] As shown in graph 311, suppose that the water supply has been turned on or water usage has increased for a certain real estate identified by an address. Looking at real estate advertising data 301 immediately prior to that water usage, it can be seen that the advertised price has been lowered. As a result, it can be determined that by lowering the advertised selling price, it became easier to conclude a deal, a deal was reached, and a new tenant moved in. Then, the "concluded price" can be obtained as an explanatory variable, and from the "period from advertising at that contract price to the conclusion of the deal," the "presence or absence of a deal in each period" can be obtained as the objective variable.

[0023] Although it is not possible to know whether a property has actually been sold when the real estate advertisements have simply disappeared, by combining this with lifeline data, it is possible to estimate the closing price with a high degree of accuracy. The total period during which no one was living there (vacant period) contributes to estimating the probability of closing as an explanatory variable, and whether or not a deal was closed is used as the objective variable. Open data 304 includes the distance from the station, the time to the Shinkansen station, etc. The age of the actual occupant and the number of people in the household, which can be obtained from the Basic Resident Register 303, are also explanatory variables.

[0024] Next, whether or not a deal was concluded within a specified period of time for the asking price of that property is learned as training data. For example, assume that a property was put up for sale for 30 million yen and then concluded a deal six months later. In this case, in the learning to generate a three-month closing probability model, the explanatory variables of that property (sales price, location, age, whether or not it has been renovated, the time since renovation, building structure, total floor area, owner attributes, etc.) are learned as data of properties that did not sell (0 data). On the other hand, in the learning to generate a six-month closing probability model, a nine-month closing probability model, and a 12-month closing probability model, the same explanatory variables of that property are learned as closing price data of properties that were sold (1 data).

[0025] In other words, it detects when a real estate deal has been concluded and learns the attributes and contract price of the concluded real estate. By looking at changes in water usage and the time when the water tap was turned on, as an example of lifeline data, it estimates the time of the deal and learns whether the data is 0 data or 1 data depending on the period from the start of advertising to the time of the deal.

[0026] Historical sales price data such as monthly real estate advertisements are used as real estate advertisement data 301. Lifeline data 302 is not limited to water, but may be changes in electricity, gas, and other charges and start dates of use. Also, in addition to the resident basic register 303, information on residents such as registration and property tax payment status may be used.

[0027] The open data 304 included in the explanatory variables includes real estate location information such as not only the address but also the distance to the nearest train station, the distance from a Shinkansen station, the surrounding population, and the rental rate.

[0028] The attributes of the owner included in the explanatory variables include, but are not limited to, age, sex, family structure, annual income, assets, and the like derived from the Basic Resident Register 303 or the like.

[0029] Through the above learning, four models are simultaneously generated, for example, a 3-month forecasting model 305, a 6-month forecasting model 306, a 9-month forecasting model 307, and a 12-month forecasting model 308. Here, a contract probability estimation model is generated for each of these four periods, but the present invention is not limited to this. The periods may be divided into smaller periods, or a model for predicting a shorter period such as one month or a model for predicting a longer period such as 36 months may be generated.

[0030] By inputting various real estate attributes into such a contract probability estimation model, the user can be presented with graphs 309, 310 showing the change in the contract probability for the price in different time periods. By inputting the attributes of the real estate he or she wishes to sell and the desired selling price, the user can grasp the probability of a contract in how long a period it will take and can accurately review the desired selling price. For example, for a house that the user wishes to sell quickly, the price can be lowered to increase the probability of a contract. In this case, if it is found that the probability of a contract does not change significantly even if the selling price is lowered below a certain amount, that price is determined to be the appropriate selling price that will obtain a high probability of a contract.

[0031] On the other hand, if profit is prioritized, it is possible to decide to set the desired selling price at the highest selling price (e.g. 60 million yen) within a specified range (e.g. medium) with a probability of success over a relatively long period (e.g. 12 months). In other words, it can be used as a sales strategy for vacant housing units and a tool for promoting distribution. If such a system is introduced to a local government, users living in that local government will be able to easily plan sales strategies for the real estate they want to sell and will be able to more accurately grasp the appropriate desired selling price. In turn, it is expected that the probability of real estate sales being successful within a certain period of time in that local government will increase, and the number of vacant homes will decrease. If age is entered when making a prediction, the system can also be used to select advertising targets, such as how much the accuracy differs between people in their 20s and those in their 50s.

[0032] 4 is a diagram showing the configuration of an information processing device 400 according to this embodiment. The information processing device 400 includes a model generation unit 401, a contract probability calculation unit 402, and a display data generation unit 403.

[0033] The model generation unit 401 generates deal probability estimation models 305 to 308 that estimate deal probabilities by learning from past real estate deal records 410 as training data.

[0034] The closing probability calculation unit 402 inputs information 420 about the real estate to be sold as input data to the closing probability estimation models 305 to 308, and calculates the closing probability for each real estate sales price.

[0035] The display data generating unit 403 generates display data for displaying an image showing the change 430 in the probability of closing a deal due to differences in real estate sales prices.

[0036] The closing probability estimation models 305 to 308 are prepared separately for each of the different sales periods, and the closing probability calculation unit 402 calculates the closing probability for each real estate sales price for each different sales period.

[0037] The display data generating unit 403 generates display data for displaying an image showing the change in the probability of closing a deal due to differences in real estate sales prices for different sales periods.

[0038] The model generation unit 401 learns whether or not a deal has been concluded for each property and for each period from when the contract price is presented until a person moves in, as a target variable, and generates the contract probability estimation models 305-308. That is, the model generation unit 401 detects properties that are estimated to be concluded and their estimated contract prices, and learns whether or not a deal has been concluded within a predetermined period (here, a period of 3 to 12 months) from when the contract price is presented.

[0039] The model generation unit 401 may generate the closing probability estimation models 305 to 308 by learning, for each property, the period during which no one lives and the contract price as objective variables. The model generation unit 401 may generate the closing probability estimation models 305 to 308 by learning, for each property, at least the contract price and the period from when the contract price is presented until when someone moves in as objective variables.

[0040] Here, the model generation unit 401 determines the timing when a person moved into a property using at least one of the lifeline data 302 and the basic resident register 303.

[0041] The model generation unit 401 further learns the contract price and contract time estimated from the real estate advertising data 301 (changes in the prices offered by real estate sales agents) and generates contract probability estimation models 305-308.

[0042] The lifeline data 302 is data on opening and closing valves or meter readings for water, electricity, or gas.

[0043] The model generating unit 401 may further use the resident register 303 or the like to learn at least one of the purchaser's age, sex, family structure, annual income, and assets as an explanatory variable to generate the contract probability estimation models 305 to 308.

[0044] The model generation unit 401 may further use registration information, open data, etc. to learn any of the location of the real estate, age of the building, building structure, area, number of floors, presence or absence of access to a road, and presence or absence of renovation as explanatory variables to generate the closing probability estimation models 305 to 308.

[0045] The contract probability calculation unit 402 uses such contract probability estimation models 305 to 308 to calculate the probability and time of a contract depending on the selling price.

[0046] 4B, the model generating unit 401 may store data contents 412, data to be used 413, and input data 414 to be used as explanatory variables of the learning model in association with a local government owned data name 411. Examples of the input data 414 to be used as explanatory variables include, but are not limited to, water usage from water usage information, the number of people in a household (household composition) from a basic resident register, the number of days since moving in, the age of residents including the age of the head of the household, the number of days since the fixed asset tax register, the age of the building, and the age of the building from real estate registration.

[0047] FIG. 5 is a flowchart showing the flow of processing performed by the information processing device 400. First, in step S501, the lifeline data 302 and the basic resident register 303 are used to comprehensively detect occupancy of real estate. Next, in step S502, various data related to the real estate for which occupancy has been detected are input as teacher data. Specifically, real estate information 501, resident information 502, and estimated selling price 503 are input as explanatory variables. The real estate information 501 includes the address, age, building structure, area, number of floors, presence or absence of access to a road, presence or absence of renovation, and time since renovation. The resident information 502 includes the number of people in the household, family structure, age, and the like of the resident who was occupying the property. In step S503, the entered teacher data is used to construct the contract probability estimation models 305 to 308. Furthermore, in step S504, the prediction accuracy is calculated.

[0048] Next, moving to the closing probability estimation phase, in step S511, the closing probability for each period and price is estimated using the generated closing probability estimation models 305-308. At this time, real estate information 551 and residence information 552 related to the real estate the user wants to sell are used as input data. The real estate information 551 includes the address, age, building structure, area, number of floors, whether or not it has access to a road, whether or not it has been remodeled, and the period since it was remodeled. The residence information 552 includes the period the house has been vacant. The desired selling price may also be used as input data.

[0049] In step S512, the probability of closing the contract for each amount of money is calculated for each period of time. At this time, amounts with high, medium, and low probability of closing the contract may be calculated.

[0050] In step S513, the change in the probability of a contract depending on the price is displayed for each period, i.e., the increase in the probability of a contract depending on how much the price is lowered is estimated and displayed.

[0051] FIG. 6 is a diagram showing the calculated closing probability distribution 601. FIG. 6 shows the closing probability for each real estate price and period until sale in the learning and validation of the closing probability model. From FIG. 6, it can be seen that low-priced real estate properties have a long sales period and take a long time to be marketed. It can also be seen that for properties with medium real estate prices, it is possible to expect early market entry by improving the attractiveness of the property through renovations, etc.

[0052] Fig. 7 is a diagram showing prediction accuracy 701. Of the prepared learning data, 30% of the data was not used for learning but was used as test data to verify the performance of the model. As shown in Fig. 7, as a result of the performance verification using the test data, it became possible to predict whether a deal would be concluded or not with an accuracy of 93.0%.

[0053] 8 is a diagram showing the GUI of a data input screen 801 displayed when the information processing device 400 is accessed from the user terminal of a user who wishes to sell real estate. The location of the real estate to be sold is specified on the map 801, and further, the desired selling price 802, postal code 803, building age 804, building structure 805, whether or not it has been renovated 806, and the period since renovation 807 are input. When the confirm button 808 is selected with these information input, the screen transitions to a display screen 901 showing the estimated probability of closing, as shown in FIG.

[0054] [Third embodiment] Next, an information processing device according to a third embodiment of the present invention will be described. The information processing device according to this embodiment differs from the second embodiment in that the selling price (estimated used property price) that achieves a predetermined probability of closing is mapped on a map. Since the other configurations and operations are the same as those of the second embodiment, the same configurations and operations are denoted by the same reference numerals and detailed description thereof will be omitted.

[0055] The closing probability calculation unit 1002 uses various models to determine an estimated selling price that will achieve a predetermined closing probability (e.g., 80%) in a predetermined period (e.g., six months) for each property on the map. Then, the display data generation unit 1003 uses the map data and the estimated selling price (used property price) to generate a mapping image of the selling price that will achieve the predetermined closing probability.

[0056] According to this embodiment, the estimated prices of used properties can be mapped on a map, making it possible to provide useful information to a user who is considering purchasing a used property, for example.

[0057] [Fourth embodiment] Next, an information processing device according to a fourth embodiment of the present invention will be described with reference to Fig. 11. The information processing device according to this embodiment differs from the second embodiment in that it generates models by age and family structure. Other configurations and operations are the same as those of the second embodiment, so the same configurations and operations are denoted by the same reference numerals and detailed descriptions thereof will be omitted.

[0058] The model generation unit 1101 acquires the age and family structure of the person (purchaser, resident) who is estimated to have concluded a contract from the resident basic register and contract information, and then generates age-specific contract probability estimation models 1121 to 1124.

[0059] If the age of the person wishing to sell is in their 20s in the real estate for sale information 420, the contract probability calculation unit 1102 calculates the contract probability 1130 using the contract probability estimation model for people in their 20s 1121. Here, the models are divided by age, but models may be prepared according to family structure. For example, there are a contract probability estimation model for a single person living alone, a contract probability estimation model for a couple with no children, a contract probability estimation model for a couple with one child, a contract probability estimation model for a couple with two children, a contract probability estimation model for a couple with three children, a contract probability estimation model for a two-generation household, and so on.

[0060] According to this embodiment, it is possible to calculate the optimal sales price and property information (whether or not the property has been remodeled, etc.) that will result in reoccupancy according to age and family structure. For example, for a family in their 30s with children, the probability of reoccupancy occurring within three months at 20 million yen is 20%, while for a dual-income couple in their 40s, the probability of reoccupancy occurring within three months at the same price is 10%. In this way, the probability of closing a deal according to the age of the seller can be calculated with high accuracy.

[0061] [Other embodiments] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the technical scope of the present invention. In addition, systems or devices that combine the separate features included in each embodiment in any way are also included in the technical scope of the present invention.

[0062] The present invention may be applied to a system consisting of multiple devices, or to a single device. Furthermore, the present invention is also applicable to a case where an information processing program for implementing the functions of the embodiments is supplied to a system or device and executed by a built-in processor. In order to implement the functions of the present invention with a computer, a program installed on a computer, a medium storing the program, a server for downloading the program, and a processor for executing the program are also included in the technical scope of the present invention. In particular, at least a non-transitory computer readable medium storing a program for causing a computer to execute the processing steps included in the above-mentioned embodiments is included in the technical scope of the present invention.

Claims

1. a calculation unit that inputs real estate information as input data into a transaction probability estimation model that estimates a transaction probability, the transaction probability estimation model being generated by learning from past transaction records of real estate as training data, and calculates a transaction probability for each real estate sales price; a generating unit that generates display data for displaying an image showing a change in the probability of closing a deal depending on the difference in the real estate selling price; Equipped with The closing probability estimation model is generated by an information processing device that learns whether or not a deal has been concluded for each piece of real estate and for each period from when the closing price is presented to when a person moves in, using the presence or absence of a deal as a target variable.

2. The information processing device according to claim 1 , wherein the timing at which the person moved in is determined using at least one of basic resident register data and lifeline data.

3. determining the time when the person moved in using at least one of basic resident register data and lifeline data; The information processing device according to claim 1 , wherein the contract probability estimation model is generated by learning a contract price estimated from a transition in the asking price of a real estate sales agent and a timing at which the person moves in.

4. 4. The information processing device according to claim 2, wherein the lifeline data is data on opening and closing valves or meter readings of water, electricity, or gas.

5. A calculation unit that inputs real estate information as input data into a transaction probability estimation model that estimates the probability of a transaction, the transaction probability estimation model being generated by learning from past transaction records of real estate as training data, and calculates the probability of a transaction for each real estate sales price; a generating unit that generates display data for displaying an image showing a change in the probability of closing a deal depending on the difference in the real estate selling price; Equipped with The information processing device generates the closing probability estimation model by learning at least the closing price and the period from when the closing price is presented until the person moves in for each piece of real estate as objective variables.

6. The closing probability estimation model is prepared separately for each of different sales periods, and the calculation unit calculates the closing probability for each real estate sales price for each different sales period, The information processing apparatus according to claim 1 , wherein the generating unit generates display data for displaying an image showing a change in the probability of closing a sale due to a difference in real estate sales price for each different sales period.

7. The information processing apparatus according to claim 1 , wherein the contract probability estimation model is generated by learning at least one of the purchaser's age, sex, family structure, annual income, and assets as an explanatory variable.

8. The information processing device according to claim 1 or 5, wherein the contract probability estimation model is generated by learning any one of the location of the real estate, the age of the building, the building structure, the area, the number of floors, whether or not it has access to a road, and whether or not it has been renovated as an explanatory variable.

9. a calculation step in which the calculation unit inputs real estate information as input data into a transaction probability estimation model that estimates a transaction probability, the transaction probability estimation model being generated by learning from past transaction records of real estate as training data, and calculates a transaction probability for each real estate sales price; a generation step of generating display data for displaying an image showing a change in the probability of closing a deal depending on a difference in the real estate selling price by a generation unit; Including, The information processing method in which the closing probability estimation model is generated by learning, as a target variable, whether or not a deal has been concluded for each piece of real estate and for each period from when the closing price is presented to when the person moves in.

10. a calculation step of inputting real estate information as input data into a transaction probability estimation model that estimates the probability of a transaction, the model being generated by learning from past transaction records of real estate as training data, and calculating the probability of a transaction for each real estate sales price; a generating step of generating display data for displaying an image showing a change in the probability of closing a deal depending on the difference in the real estate selling price; An information processing program for causing a computer to execute the following: The said contract probability estimation model is an information processing program which is generated by learning whether or not a contract has been concluded for each said property and for each period from when the contract price is presented to when the person moves in, as a target variable.

Images