Risk identification method and product for house mortgage loan business
By identifying similar data subsets of target houses and users in the housing mortgage business, the problem of low efficiency and accuracy of risk identification after housing mortgage loans in the existing technology is solved, and more efficient risk identification and early warning is achieved, reducing the loss of bank assets.
Patent Information
- Application Number
- CN202411894171.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-20
- Publication Date
- 2025-04-11
AI Technical Summary
The prior art has low efficiency and accuracy in post-housing mortgage risk identification, especially when facing multi-dimensional and multi-variable data.
By obtaining user data sets and house data sets associated with housing mortgage business, responding to credit risk events, identifying target houses and target users, forming a similar data subset based on the house and user characteristics, identifying suspected houses that may have credit risks and providing early warnings.
It improves the efficiency and accuracy of risk identification after mortgage loans, helps banks manage assets more effectively and reduce potential losses.
Smart Images
Figure CN119809811A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of financial technology, and in particular to a risk identification method, device, equipment, computer-readable storage medium and computer program product for housing mortgage loan business. Background Art
[0002] One of the current mainstream loan methods is to obtain a bank loan by mortgaging the house to the bank. Post-loan management of house mortgages is crucial for banks, as it aims to ensure the quality of loan assets, prevent and reduce credit risks, and protect the safety of bank assets.
[0003] At present, the post-loan risk assessment method for housing mortgages mainly relies on manual review and simple statistical models, which makes it difficult to accurately predict potential risks. Especially when faced with multi-dimensional and multi-variable data, the traditional post-loan risk identification efficiency and accuracy are low. Summary of the invention
[0004] The embodiments of the present application provide a risk identification method, device, equipment, computer-readable storage medium and computer program product for housing mortgage loan business, so as to solve the technical problems of low efficiency and accuracy in post-loan risk identification of housing mortgage loans.
[0005] In a first aspect, an embodiment of the present application provides a risk identification method for a housing mortgage loan business, comprising:
[0006] Obtain user data sets and housing data sets associated with housing mortgage business;
[0007] In response to a credit risk event being triggered, determining a target house associated with the credit risk event, and determining a plurality of houses most similar to the target house from the house data set based on house features of the target house to form a first house data subset;
[0008] Determine a target user to which the target house belongs, and based on user characteristics of the target user, determine a plurality of users most similar to the target user from the user data set to form a user data subset;
[0009] Determining houses associated with each user in the user data subset to form a second house data subset;
[0010] Based on the first housing data subset and the second housing data subset, suspected housing with credit risk is determined, and an early warning is issued for the suspected housing.
[0011] In a second aspect, an embodiment of the present application provides a risk identification device for housing mortgage loan business, comprising:
[0012] An acquisition module is used to acquire user data sets and house data sets associated with housing mortgage business;
[0013] A processing module is used to, in response to a credit risk event being triggered, determine a target house associated with the credit risk event, determine multiple houses most similar to the target house from the house data set based on the house characteristics of the target house, and form a first house data subset; determine a target user to whom the target house belongs, determine multiple users most similar to the target user from the user data set based on the user characteristics of the target user, and form a user data subset; determine houses associated with each user in the user data subset, and form a second house data subset; determine suspected houses with credit risks based on the first house data subset and the second house data subset, and issue an early warning for the suspected houses.
[0014] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the risk identification method for housing mortgage loan business provided in the first aspect of the embodiment of the present application are implemented.
[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the risk identification method for housing mortgage loan business provided in the first aspect of the embodiment of the present application are implemented.
[0016] In a fifth aspect, an embodiment of the present application provides a computer program product having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the risk identification method for housing mortgage loan business provided in the first aspect of the embodiment of the present application are implemented.
[0017] The technical solution provided by the embodiment of the present application determines multiple houses that are most similar to the target house from the house data set through the house characteristics of the target house associated with the credit risk event to form a first house data subset; determines the target user to which the target house belongs, and based on the user characteristics of the target user, determines multiple users that are most similar to the target user from the user data set to form a user data subset; determines the houses associated with each user in the user data subset to form a second house data subset; based on the first house data subset and the second house data subset, determines suspected houses that may have credit risks, and issues an early warning for the suspected houses. By adopting the embodiment of the present application, suspected houses that may have credit risks can be mined from massive house mortgage data, thereby improving the efficiency and accuracy of post-loan risk identification of house mortgages, thereby effectively reducing the loss of bank assets. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 A schematic diagram of a process flow of a risk identification method for a housing mortgage loan business provided in an embodiment of the present application;
[0019] Figure 2 Another schematic diagram of a process flow of a risk identification method for a housing mortgage loan business provided in an embodiment of the present application;
[0020] Figure 3 A schematic diagram of clustering results of a user data set and a house data set provided in an embodiment of the present application;
[0021] Figure 4 A schematic diagram of a structure of a risk identification device for housing mortgage loan business provided in an embodiment of the present application;
[0022] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application are further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Those skilled in the art can make adjustments to them as needed to suit specific application scenarios. It should also be noted that, for ease of description, only the parts related to the present application are shown in the accompanying drawings, rather than all structures.
[0024] It should be noted that the information collected in the embodiments of the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0025] Figure 1 A flow chart of a risk identification method for a housing mortgage loan business provided in an embodiment of the present application. Figure 1 As shown, the method may include:
[0026] S101, obtaining a user dataset and a house dataset associated with a house mortgage loan business.
[0027] Specifically, the user data set includes attribute information of each user associated with the housing mortgage loan business, such as the gender, age, liquidity, income status, etc. of the user (i.e., the borrower); the housing data set includes information on mortgaged properties under the names of each user associated with the housing mortgage loan business. Each property may also include some attribute information, such as property price, geographical location, and area, etc.
[0028] In the specific implementation, the data related to the housing mortgage loan can be extracted from the database of the bank's loan management system, and the above user data set and housing data set can be determined based on the extracted data. In addition, the association between the above user data set and housing data set can be established to ensure that each house in the housing data set is associated with the corresponding user in the user data set. For example, assuming that the user data set P = {c1, c2...c n}, housing data set H = {h1, h2…h n}, there is a corresponding relationship R = {(c1, h1), (c2, h2), (c3, h3)…(c n ,h n )}.
[0029] S102: In response to a credit risk event being triggered, a target house associated with the credit risk event is determined, and based on house features of the target house, multiple houses most similar to the target house are determined from a house data set to form a first house data subset.
[0030] Among them, credit risk events refer to events that may cause bank loan losses, such as multiple mortgages of houses, houses being sealed by courts, and houses being damaged. In specific implementation, potential credit risk events can be monitored in real time through external data sources (such as court records, public registration information, media reports, etc.). In response to detected credit risk events, the detailed information of the credit risk events is matched with the bank's real estate mortgage data set to determine the target house associated with the credit risk event.
[0031] S103: Determine the target user to which the target house belongs, and based on the user characteristics of the target user, determine multiple users who are most similar to the target user from the user data set to form a user data subset.
[0032] The target user refers to the user to whom the target house belongs. The target user to whom the target house belongs can be determined based on the association relationship between the user data set and the house data set (such as the corresponding relationship R described in S101 above). Next, the user characteristics of the target user are used to determine multiple users most similar to the target user from the user data set using algorithms such as K nearest neighbor algorithm, decision tree or random forest, and the data of these multiple users determined form a user data subset. The above user characteristics may include but are not limited to: user demographic characteristics (such as age, education level, gender, etc.), economic status (such as income level, asset value, debt situation, credit score, employment status), behavioral characteristics (such as bank transaction history, shopping habits, payment behavior, financial planning, etc.) and geographical location characteristics (such as residence, house type, community characteristics, etc.).
[0033] S104. Determine the house associated with each user in the user data subset to form a second house data subset.
[0034] Based on the association relationship between the user data set and the house data set (such as the corresponding relationship R described in S101 above), the houses associated with each user in the user data subset are determined, and the determined data of these houses form a second house data subset.
[0035] S105. Based on the first housing data subset and the second housing data subset, determine suspected housing with credit risk, and issue an early warning for the suspected housing.
[0036] After obtaining the first housing data subset and the second housing data subset, suspected housing with credit risk can be determined from the first housing data subset and the second housing data subset, and a pre-set method can be used to issue an early warning to the suspected housing.
[0037] In this step, when a suspected house with credit risk is determined, the suspected house can be displayed in a preset manner different from the general display method to attract the attention of risk control managers, thereby achieving the purpose of early warning.
[0038] The preset method may include one or more combinations of highlighting, flashing, background color highlighting, font color highlighting, etc., to remind that there are suspected houses with credit risks in the current mortgage housing collection.
[0039] Optionally, it can be combined with other methods as needed, such as sending prompt information to the mailbox or terminal of the risk control manager, using a buzzer alarm, etc., so as to achieve the purpose of early warning from different dimensions or angles and further ensure the effect of the early warning.
[0040] Optionally, the above-mentioned determination of suspected houses with credit risk based on the first house data subset and the second house data subset may include: selecting overlapping houses that exist simultaneously in the first house data subset and the second house data subset, and determining the overlapping houses as suspected houses with credit risk. That is, the overlapping houses that exist simultaneously in the first house data subset and the second house data subset can be screened out, and these overlapping houses are houses that are risk-associated with the target house from both the user dimension and the house dimension, and the probability of them having credit risk is relatively high. Therefore, these overlapping houses can be determined as suspected houses with credit risk.
[0041] The risk identification method for housing mortgage business provided by the embodiment of the present application determines multiple houses most similar to the target house from the housing data set through the house characteristics of the target house associated with the credit risk event to form a first housing data subset; determines the target user to which the target house belongs, and based on the user characteristics of the target user, determines multiple users most similar to the target user from the user data set to form a user data subset; determines the houses associated with each user in the user data subset to form a second housing data subset; based on the first housing data subset and the second housing data subset, determines suspected houses that may have credit risks, and issues an early warning for the suspected houses. By adopting the embodiment of the present application, suspected houses that may have credit risks can be mined from massive housing mortgage data, thereby improving the efficiency and accuracy of post-loan risk identification of housing mortgages, thereby effectively reducing the loss of bank assets.
[0042] Figure 2 Another flow chart of the risk identification method for housing mortgage loan business provided in the embodiment of the present application. Figure 2 As shown, the method may include:
[0043] S201, obtaining a user dataset and a house dataset associated with a house mortgage loan business.
[0044] Optionally, after obtaining the user data set and the house data set, the non-numeric attributes in the user data set and the house data set may be quantized to convert the non-numeric attributes into numeric attributes. For example, the non-numeric attributes may be quantized by referring to the following formula:
[0045]
[0046] Among them, a is the non-numeric attribute in the user data set, ha is the non-numeric attribute in the house data set, threshold is the preset threshold, and value is the quantized numeric attribute.
[0047] For example, for the user's gender attribute, if it is "male", it is quantified to 1, and if it is "female", it is quantified to 0.
[0048] Furthermore, the numerical attributes may be standardized. For example, the numerical attributes may be standardized with reference to the following formula:
[0049]
[0050] Among them, μ is the data mean of a certain attribute, σ is the standard deviation, x is the numerical attribute to be standardized, and x new is the normalized attribute value.
[0051] S202: Cluster the house data set based on the house features of each house in the house data set to obtain a first clustering result.
[0052] In this step, the binary K-Means clustering algorithm can be used to cluster the house data set. The specific clustering process can be as follows:
[0053] 1. Initialization: treat all data points in the house data as a cluster;
[0054] 2. Select the cluster to be split: Select a cluster from the current cluster to split, and the selection criterion is the cluster with the largest sum of squared errors. The sum of squared errors can be calculated using the following formula:
[0055]
[0056] Among them, C i are all the data points in the ith cluster, and x is C i A data point in the cluster, μ i It is cluster C i The center of mass.
[0057] Cluster C i The centroid of can be calculated by the following formula:
[0058]
[0059] 3. Splitting operation: Apply the standard K-Means clustering method to the selected clusters, setting K=2.
[0060] 4. Evaluation: Determine whether the preset number of clusters is reached. If so, clustering is completed and the first clustering result is obtained; otherwise, return to step 2 and continue to select new clusters for splitting until the preset number of clusters is reached.
[0061] S203: Cluster the user data set based on the user characteristics of each user in the user data set to obtain a second clustering result.
[0062] In this step, the user data set can be clustered using a binary K-Means clustering algorithm. The specific clustering operation process can refer to the description in S202 above, which will not be repeated in this embodiment. The data relationship after clustering can be as follows: Figure 3 shown.
[0063] S204: In response to a credit risk event being triggered, determine a target house associated with the credit risk event, and determine a first target cluster where the target house is located from the first clustering result.
[0064] S205 . Based on the house features of the target house, determine a plurality of houses that are most similar to the target house from the first target cluster to form a first house data subset.
[0065] After obtaining the target house, the first target cluster where the target house is located can be determined from the first clustering result, and based on the house characteristics of the target house, multiple houses that are most similar to the target house can be determined from the first target cluster through the K nearest neighbor algorithm to form a first house data subset. In this way, in the process of determining multiple houses that are most similar to the target house, it is only necessary to search in the first target cluster, which simplifies the search scope and improves the efficiency of risk identification.
[0066] Assume that the target house h j The first target cluster D = {h1, h2...h j …h k}, the specific process of determining the first housing data subset can be:
[0067] 1. Calculate the distance: Calculate the distance between the house data points in the first target cluster D and h j The specific calculation formula is as follows:
[0068]
[0069] Among them, h i is the house data point in the first target cluster D, m is the number of features of the house data point, d(h j ,h i ) is the house data point h i With h j The distance between.
[0070] 2. Select d nearest neighbors: Sort the distances calculated above in ascending order, and select d nearest neighbors with h. j The nearest property is recorded as the first housing data subset List1 (h1, h2, h3…h d ).
[0071] S206: Determine the target user to which the target house belongs, and determine the second target cluster to which the target user belongs from the second clustering result.
[0072] S207 . Based on the user characteristics of the target user, determine a plurality of users most similar to the target user from the second target cluster to form a user data subset.
[0073] After obtaining the target user, the second target cluster where the target user is located can be determined from the second clustering result, and based on the user characteristics of the target user, multiple users most similar to the target user can be determined from the second target cluster by using the K nearest neighbor algorithm to form a user data subset. For example, e users most similar to the target user are selected to form a user data subset List2 (c1, c2, c3…c e ). The specific process of determining the user data subset may refer to the description in S205 above, which will not be described in detail in this embodiment.
[0074] S208. Determine the house associated with each user in the user data subset to form a second house data subset.
[0075] Based on the association relationship between the user data set and the house data set (such as the corresponding relationship R described in S101 above), the house associated with each user in the user data subset is determined to form a second house data subset List3 (h1, h2, h3...h f ).
[0076] S209: Based on the first housing data subset and the second housing data subset, determine suspected housing with credit risk, and issue an early warning for the suspected housing.
[0077] In this step, List1 (h1, h2, h3…h d ) and List3(h1, h2, h3…h f ) are identified as suspected houses with credit risks.
[0078] In this embodiment, a clustering algorithm is used to divide the user data set into different groups based on the user characteristics of each user in the user data set, and a clustering algorithm is used to divide the house data set into different groups based on the house characteristics of each house in the house data set. This enables the system to more accurately and quickly identify users and houses with similar characteristics to the target houses, thereby improving the accuracy and efficiency of credit risk identification.
[0079] Based on the above embodiment, optionally, the above-mentioned early warning for the suspected house may include: evaluating the risk level of the suspected house based on the house information of the suspected house and the user information of the user to whom the suspected house belongs; and issuing an early warning for the suspected house based on an early warning method corresponding to the risk level.
[0080] Specifically, the house information of the suspected house can be extracted from the bank's database, including the market value, geographical location, area, construction age, etc. of the house, and the relevant information of the user to whom the suspected house belongs can be obtained, including the user's credit score, repayment history, income level, employment status, etc., and then the features related to the risk level assessment can be extracted from the obtained original data, and the risk level of the suspected house can be determined based on the extracted features. Among them, the above-mentioned features can be the ratio of the house's value to the loan balance, the user's debt-to-income ratio, the number of repayment delays of the user, and the trend of changes in the house value. It can be understood that if the user's debt-to-income ratio is higher, the number of repayment delays is more, and the ratio of the house's value to the loan balance is lower, the credit risk level of the suspected house is higher. Conversely, if the user's debt-to-income ratio is lower, the number of repayment delays is fewer, and the ratio of the house's value to the loan balance is higher, the credit risk level of the suspected house is lower.
[0081] The above risk levels can be divided into multiple different levels, such as low risk, medium risk and high risk. After determining the risk level of the suspected house, the suspected house can be warned in a corresponding manner based on the risk level. For example, when displaying the suspected house in a preset manner different from the general display method, different colors can be used to highlight the suspected houses of different risk levels. For suspected houses with high risk levels, risk control managers can also be notified through instant messaging tools or alarm systems to achieve a rapid response to high-risk credit events.
[0082] Furthermore, risk response strategies for suspected houses can be determined based on risk levels, and the risk response strategies can be output to assist risk control managers in handling suspected houses. For example, new repayment plans can be automatically generated for suspected houses with high and medium risk levels; for suspected houses with low risk levels, corresponding repayment incentives can be matched with user information to encourage users to repay in advance, etc.
[0083] In this embodiment, by evaluating the risk level of suspected houses, warnings are issued to suspected houses based on warning methods corresponding to the risk levels and corresponding risk response measures are generated, thereby improving the intelligence of post-mortgage risk management for housing mortgages, and being able to reasonably allocate risk management resources according to risk levels, ensuring that houses with high risk levels receive special attention, thereby reducing bank asset loss.
[0084] Figure 4 A schematic diagram of a risk identification device for housing mortgage loan business provided in an embodiment of the present application. Figure 4 As shown, the device may include an acquisition module 401 and a processing module 402 .
[0085] Specifically, the acquisition module 401 is used to acquire a user data set and a house data set associated with a house mortgage loan business;
[0086] Processing module 402 is used to determine, in response to a credit risk event being triggered, a target house associated with the credit risk event, and based on the house characteristics of the target house, determine multiple houses that are most similar to the target house from the house data set to form a first house data subset; determine a target user to whom the target house belongs, and based on the user characteristics of the target user, determine multiple users that are most similar to the target user from the user data set to form a user data subset; determine the house associated with each user in the user data subset to form a second house data subset; based on the first house data subset and the second house data subset, determine a suspected house with credit risk, and issue an early warning for the suspected house.
[0087] Based on the above embodiment, optionally, the processing module 402 is further configured to cluster the house data set based on the house features of each house in the house data set to obtain a first clustering result after obtaining the user data set and the house data set associated with the house mortgage loan business;
[0088] Correspondingly, the processing module 402 is also used to determine the first target cluster where the target house is located from the first clustering result; based on the house features of the target house, determine multiple houses most similar to the target house from the first target cluster to form a first house data subset.
[0089] Based on the above embodiment, optionally, the processing module 402 is further configured to cluster the user data set based on user characteristics of each user in the user data set to obtain a second clustering result after obtaining the user data set and the house data set associated with the house mortgage loan business;
[0090] Correspondingly, the processing module 402 is further used to determine the second target cluster where the target user is located from the second clustering result; based on the user characteristics of the target user, determine multiple users most similar to the target user from the second target cluster to form a user data subset.
[0091] Based on the above embodiment, optionally, the processing module 402 is further configured to select overlapping houses that exist simultaneously in the first house data subset and the second house data subset, and determine the overlapping houses as suspected houses with credit risks.
[0092] Based on the above embodiment, optionally, the processing module 402 is also used to evaluate the risk level of the suspected house based on the house information of the suspected house and the user information of the user to whom the suspected house belongs; and to issue an early warning to the suspected house based on the early warning method corresponding to the risk level.
[0093] Based on the above embodiment, optionally, the processing module 402 is further configured to determine a risk response strategy for the suspected house based on the risk level, and output the risk response strategy.
[0094] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 5 As shown, the device includes a processor 50, a memory 51, an input device 52 and an output device 53; the number of the processor 50 in the device can be one or more. Figure 5 A processor 50 is taken as an example; the processor 50, memory 51, input device 52 and output device 53 in the device can be connected by a bus or other means. Figure 5 The example of connecting through bus is taken in the following.
[0095] The memory 51 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the risk identification method for housing mortgage business in the embodiments of the present application (for example, the acquisition module 401 and the processing module 402 in the risk identification device for housing mortgage business). The processor 50 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 51, that is, implements the risk identification method for housing mortgage business provided in any of the above embodiments.
[0096] The memory 51 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created during the risk identification process for a housing mortgage loan business, etc. In addition, the memory 51 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 51 may further include a memory remotely arranged relative to the processor 50, and these remote memories may be connected to the device / terminal / server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0097] The input device 52 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 53 may include a display device such as a display screen.
[0098] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:
[0099] Obtain user data sets and housing data sets associated with housing mortgage business;
[0100] In response to a credit risk event being triggered, determining a target house associated with the credit risk event, and determining a plurality of houses most similar to the target house from the house data set based on house features of the target house to form a first house data subset;
[0101] Determine a target user to which the target house belongs, and based on user characteristics of the target user, determine a plurality of users most similar to the target user from the user data set to form a user data subset;
[0102] Determining houses associated with each user in the user data subset to form a second house data subset;
[0103] Based on the first housing data subset and the second housing data subset, suspected housing with credit risk is determined, and an early warning is issued for the suspected housing.
[0104] In one embodiment, a computer program product is further provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0105] Obtain user data sets and housing data sets associated with housing mortgage business;
[0106] In response to a credit risk event being triggered, determining a target house associated with the credit risk event, and determining a plurality of houses most similar to the target house from the house data set based on house features of the target house to form a first house data subset;
[0107] Determine a target user to which the target house belongs, and based on user characteristics of the target user, determine a plurality of users most similar to the target user from the user data set to form a user data subset;
[0108] Determining houses associated with each user in the user data subset to form a second house data subset;
[0109] Based on the first housing data subset and the second housing data subset, suspected housing with credit risk is determined, and an early warning is issued for the suspected housing.
[0110] The risk identification device, electronic device, computer-readable storage medium, and computer program product for housing mortgage loan business provided in the above embodiments can execute the risk identification method for housing mortgage loan business provided in any embodiment of the present application, and have the corresponding functional modules and beneficial effects of executing the method. For technical details not described in detail in the above embodiments, please refer to the risk identification method for housing mortgage loan business provided in any embodiment of the present application.
[0111] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.
[0112] It is worth noting that the various units and modules included in the above embodiments are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.
[0113] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims
1. A risk identification method for housing mortgage loan business, characterized in that: include: Obtain user data sets and housing data sets associated with housing mortgage business; In response to a credit risk event being triggered, determining a target house associated with the credit risk event, and determining a plurality of houses most similar to the target house from the house data set based on house features of the target house to form a first house data subset; Determine a target user to which the target house belongs, and based on user characteristics of the target user, determine a plurality of users most similar to the target user from the user data set to form a user data subset; Determining houses associated with each user in the user data subset to form a second house data subset; Based on the first housing data subset and the second housing data subset, suspected housing with credit risk is determined, and an early warning is issued for the suspected housing.
2. The method according to claim 1, characterized in that After obtaining the user dataset and the house dataset associated with the house mortgage business, the method further includes: Clustering the house dataset based on the house features of each house in the house dataset to obtain a first clustering result; Correspondingly, based on the house features of the target house, a plurality of houses most similar to the target house are determined from the house data set to form a first house data subset, including: Determine a first target cluster where the target house is located from the first clustering result; Based on the house features of the target house, a plurality of houses that are most similar to the target house are determined from the first target cluster to form a first house data subset.
3. The method according to claim 1, characterized in that: After obtaining the user dataset and the house dataset associated with the house mortgage business, the method further includes: Clustering the user data set based on the user characteristics of each user in the user data set to obtain a second clustering result; Correspondingly, based on the user characteristics of the target user, multiple users most similar to the target user are determined from the user data set to form a user data subset, including: Determine a second target cluster where the target user is located from the second clustering result; Based on the user characteristics of the target user, a plurality of users most similar to the target user are determined from the second target cluster to form a user data subset.
4. The method according to claim 1, characterized in that: The step of determining suspected houses with credit risk based on the first house data subset and the second house data subset includes: Select overlapping houses that exist in both the first house data subset and the second house data subset, and determine the overlapping houses as suspected houses with credit risks.
5. The method according to claim 1, characterized in that Issue early warning to the suspected house, including: Based on the house information of the suspected house and the user information of the user to whom the suspected house belongs, assessing the risk level of the suspected house; An early warning is issued to the suspected house based on an early warning method corresponding to the risk level.
6. The method according to claim 5, characterized in that Also includes: A risk response strategy for the suspected house is determined based on the risk level, and the risk response strategy is output.
7. A risk identification device for housing mortgage loan business, characterized in that: include: An acquisition module is used to acquire user data sets and house data sets associated with housing mortgage business; a processing module, configured to, in response to a credit risk event being triggered, determine a target house associated with the credit risk event, and determine, based on house features of the target house, a plurality of houses most similar to the target house from the house data set to form a first house data subset; Determine a target user to which the target house belongs, and based on user characteristics of the target user, determine a plurality of users most similar to the target user from the user data set to form a user data subset; Determining houses associated with each user in the user data subset to form a second house data subset; Based on the first housing data subset and the second housing data subset, suspected housing with credit risk is determined, and an early warning is issued for the suspected housing.
8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.