Online pre-approval method, device, medium and electronic equipment for housing loan

Abstract

The embodiments of the present application disclose an online pre-approval method, device, medium and electronic device for housing loans. The method includes: obtaining the lender's declaration information, and executing preset risk rules to determine whether the declaration information meets the rule standards; if it does, determining the customer group to which the declaration information belongs based on the risk characteristics included in the declaration information; using the pre-approval risk control model associated with the customer group to perform risk assessment; if the risk assessment result is passed, using a preset scoring card to score the declaration information to obtain the result of online pre-approval. By implementing this solution, different pre-approval methods can be used for different customer groups to achieve the purpose of quickly and accurately pre-approving housing loans.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of machine learning technology, and in particular to an online pre-approval method, device, medium and electronic device for housing loans. Background Art

[0002] In recent years, with the rapid development of the economy and the gradual improvement of people's living standards, the proportion of housing consumption has a clear upward trend and the demand for personal housing loans is strong.

[0003] The personal housing loan business is developing rapidly. In order to ensure the safety of the loan business, the current loan business is often handled through offline application and offline approval. This method has a long process and involves many links such as application, approval, housing evaluation, mortgage registration, etc. For banks, it consumes a lot of manpower and material resources, and for customers, it affects the loan time and satisfaction. Therefore, how to achieve efficient and accurate processing of loan business has become a technical problem for the development of the industry. Summary of the invention

[0004] The embodiments of the present application provide an online pre-approval method, device, medium and electronic device for housing loans, which can adopt different pre-approval methods for different customer groups to achieve the purpose of quickly and accurately pre-approving housing loans.

[0005] In a first aspect, an embodiment of the present application provides an online pre-approval method for a housing loan, the method comprising:

[0006] Obtain the lender's declared information and execute the preset risk rules to determine whether the declared information meets the rule standards;

[0007] If it is in compliance, the customer group to which the declared information belongs is determined based on the risk characteristics included in the declared information;

[0008] Perform risk assessment using a pre-approval risk control model associated with the customer group;

[0009] If the risk assessment result is passed, the preset score card will be used to score the declared information to obtain the result of online pre-approval.

[0010] Furthermore, the declared information includes at least one of customer information, liability information and asset information.

[0011] Furthermore, after determining whether the declared information meets the rule standards, the method further includes:

[0012] If it does not meet the requirements, the lender will be notified to provide additional information offline.

[0013] Furthermore, before executing the preset risk rules to determine whether the declared information meets the rule standards, the method also includes:

[0014] Determine whether there are any co-lenders;

[0015] If yes, obtain the loan information of the loan co-lender;

[0016] Accordingly, the preset risk rules are executed to determine whether the declared information meets the rule standards, including:

[0017] The preset risk rules are executed on the declared information of the lender and the participating information of the co-borrower to determine whether the declared information meets the rule standards.

[0018] Further, according to the risk characteristics included in the declared information, determining the customer group to which the declared information belongs includes:

[0019] Obtain the risk characteristic dimensions included in the declared information;

[0020] If the risk characteristic dimension includes a target dimension, the customer group to which the declared information belongs is determined based on the risk characteristic value of the target dimension.

[0021] Furthermore, the target dimensions include city level dimension, purchased house type dimension and transaction price dimension;

[0022] Determine the customer group to which the declared information belongs based on the risk characteristic value of the target dimension, including:

[0023] The customer group to which the declared information belongs is determined based on the risk characteristic values ​​of the target dimensions including the city level dimension, the purchased house type dimension and the transaction price dimension.

[0024] Furthermore, the risk characteristic values ​​of the city level dimension include: first-tier cities, second-tier cities, and third-tier cities;

[0025] The risk characteristic values ​​of the housing type dimension include: new housing and second-hand housing;

[0026] The risk characteristic values ​​of the transaction price dimension include: higher than the preset price and lower than the preset price.

[0027] Furthermore, the preset price is determined based on the city level dimension and the house type dimension.

[0028] Furthermore, if the risk characteristic value of the city level dimension is a third-tier city, then:

[0029] The customer group to which the declared information belongs is determined based on the risk characteristic values ​​of the housing purchase type dimension.

[0030] Furthermore, the application information is scored using a preset scoring card to obtain the result of online pre-approval, including:

[0031] The declared information is scored using a preset scoring card, and if the scoring result is higher than a first threshold value, online approval recommendation information is generated.

[0032] Furthermore, the method further comprises:

[0033] If the scoring result is lower than the first threshold value and higher than the second threshold value, the declared information is determined to be low-risk information, and offline approval recommendation information is generated; wherein the second threshold value is lower than the first threshold value.

[0034] Furthermore, the method further comprises:

[0035] If the scoring result is lower than the second threshold value, the declared information is determined to be high-risk information, and offline approval recommendation information is generated.

[0036] In a second aspect, an embodiment of the present application provides an online pre-approval device for a housing loan, the device comprising:

[0037] The risk rule review module is used to obtain the lender's declared information and execute the preset risk rules to determine whether the declared information meets the rule standards;

[0038] A customer group determination module, used to determine the customer group to which the declared information belongs based on the risk characteristics included in the declared information if the audit result of the risk rule audit module is compliance;

[0039] A risk assessment module, configured to perform risk assessment using a pre-approval risk control model associated with the customer group;

[0040] The scoring module is used to score the declared information using a preset scoring card if the risk assessment result is passed, so as to obtain the result of online pre-approval.

[0041] On the third aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the online pre-approval method for a mortgage loan as described in the embodiment of the present application is implemented.

[0042] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the online pre-approval method for a mortgage as described in the embodiment of the present application is implemented.

[0043] The technical solution provided in the embodiment of the present application obtains the lender's declaration information and executes the preset risk rules to determine whether the declaration information meets the rule standards; if it does, the customer group to which the declaration information belongs is determined based on the risk characteristics included in the declaration information; a pre-approval risk control model associated with the customer group is used to perform risk assessment; if the risk assessment result is passed, the declaration information is scored using a preset scoring card to obtain the result of online pre-approval. The technical solution provided in the present application can adopt different pre-approval methods for different customer groups to achieve the purpose of quickly and accurately pre-approving mortgage loans. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of an online pre-approval method for a housing loan provided in an embodiment of the present application;

[0045] Figure 2 is a schematic diagram of another online pre-approval method for housing loans provided in an embodiment of the present application;

[0046] Figure 3 It is a structural schematic diagram of an online pre-approval device for a housing loan provided in an embodiment of the present application;

[0047] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0049] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0050] Figure 1 It is a flow chart of the online pre-approval method for housing loans provided in an embodiment of the present application. This embodiment can be applicable to elderly care services. The method can be executed by the online pre-approval device for housing loans provided in an embodiment of the present application. The device can be implemented by software and / or hardware and can be integrated into electronic devices such as smart terminals.

[0051] like Figure 1 As shown, the online pre-approval method for the mortgage includes:

[0052] S110, obtaining the lender's declared information, and executing the preset risk rules to determine whether the declared information meets the rule standards.

[0053] Among them, the lender is the person who makes a loan request, that is, the person who needs a loan to buy a house. The declared information can be the basic information of the lender himself, such as name, gender, age and place of origin, etc. It can also include other information, such as whether there is a loan record, whether it is repaid on time, etc. The risk rule can be in the form of a collection, which can include various risk review rules. The risk rule is a strategy rule generated based on business experience and data analysis. It can inform the customer whether it meets the basic access conditions in the early stage of the process, and can generate prompts for users to supplement the materials offline according to the prompts. Among them, the basic access conditions can include whether the documents are complete and whether the information is authentic.

[0054] In this embodiment, optionally, the declared information includes at least one of customer information, liability information and asset information.

[0055] Among them, customer information can include basic information and behavioral information. Basic information includes customer personal information, basic information within the bank, etc. Behavioral information can include offline behavior and terminal behavior, etc. Liability information can include credit card information and loan information, etc. Among them, credit card information includes: account information, usage, repayment status, and overdue status, etc. Loan information can include credit loans, mortgages, car loans, mortgage loans, other loans, such as decoration loans, travel loans, etc. Asset information can include investment information, financial information, deposit information, payment information, and insurance information. After authorization by the customer, the customer's internal and external bank data can be obtained, and the relevant data can be associated, integrated, and cleaned to leave a valid data set. The characteristic information mainly covers the following table:

[0056]

[0057] After the basic feature information is collected, it is necessary to derive the features to form the feature fields required for various modeling and risk control strategies. The feature derivation methods can include transparent transmission, statistical aggregation, and feature cross-talk.

[0058] For numeric fields, when a sample has only one record, such as age, education, etc., it can be directly transparently transmitted as a model input feature. For categorical variables, if there are too many types, you can merge the types and then transparently transmit them, such as student major, company type, occupation, etc., and then transparently transmit them.

[0059] Statistical aggregation is for data of flow or detail types, such as loan details, transaction flow, payroll records, etc. Each person may have multiple flow records occurring at different times. For such flow characteristics, different time windows are usually divided to calculate statistical variables within each window, such as calculating the sum, mean, quantile, minimum, maximum, and standard deviation for numeric fields. For categorical variables, the number of occurrences of the main types and the types of occurrences are calculated.

[0060] Feature crossover is a multi-dimensional crossover between features. Combining the above two methods, more features can be derived. Usually, a categorical variable and a numerical variable are combined to perform statistical aggregation on numerical variables in different categories. For example, by combining the two fields of loan type and loan balance, fields such as car loan balance, mortgage balance, and consumer loan balance can be derived.

[0061] In this solution, optionally, after determining whether the declared information meets the rule standard, the method further includes:

[0062] If it does not meet the requirements, the lender will be notified to provide additional information offline.

[0063] Among them, if the risk rule review finds that the lender's declared information does not meet the preset rule standards, a prompt message can be generated based on the reason for non-compliance to notify the lender to supplement the information offline. Through such a setting, the lender can be automatically reminded to supplement the information during the entire pre-approval stage, avoiding manual intervention and reducing the workload of the staff.

[0064] In this embodiment, optionally, before executing the preset risk rule to determine whether the declared information meets the rule standard, the method further includes:

[0065] Determine whether there are any co-lenders;

[0066] If yes, obtain the loan information of the loan co-lender;

[0067] Accordingly, the preset risk rules are executed to determine whether the declared information meets the rule standards, including:

[0068] The preset risk rules are executed on the declared information of the lender and the participating information of the co-borrower to determine whether the declared information meets the rule standards.

[0069] Among them, the co-borrower can be a person who takes out a loan together with the lender, such as the spouse of the lender, who can be a co-borrower for the mortgage. The co-borrowing information here can be similar to the declared information, such as the co-borrower's basic information, behavioral information, credit card information, loan information, and investment information and financial management information in the asset information. In the case of co-borrowers, the declared information and the co-borrowing information can be simultaneously reviewed according to the risk rules. The advantage of this setting is that when there are co-borrowers, the preset risk rules can be reviewed together based on the declared information and the co-borrowing information, and the review results can be obtained. There is no need to re-review the co-borrowers in other ways, which improves the execution efficiency of this plan and reduces the complexity of the plan implementation.

[0070] Understandably, among the numerous data features, relatively important features can be sorted out, such as the minimum available credit limit for credit cards in the past 30 days, the down payment amount for real estate, the maximum difference in months between the loan due date and the application time, the number of reasons for all types of inquiries from the People's Bank of China, the number of reasons for all types of loan approval inquiries from the People's Bank of China, the average total credit limit for People's Bank of China loans, and the number of overdue loans from the People's Bank of China.

[0071] In this solution, the risk rule engine deploys policy rules generated based on business experience and data analysis, which can inform customers early in the process that they do not meet the basic entry requirements and allow them to supplement their materials offline according to the prompts.

[0072] The content of the rules is mainly set with reference to the following three aspects: blacklist, such as: the applicant hits the bank's blacklist, the applicant hits the list of persons involved in litigation and dishonest debtors; product access conditions that can be judged by the system, such as: the customer is engaged in a restricted industry or the customer is in a restricted area, the customer's outstanding loan balance in the bank is > N yuan; rules derived from business experience and data analysis, such as: the customer's number of credit inquiries in the past 3 / 6 / 12 months is > N times, the customer's number of loan overdue months in the past 3 / 6 / 12 / 24 months is > N, the customer's number of credit card / quasi-credit card overdue months in the past 3 / 6 / 12 / 24 months is > N months, whether the customer is a credit-cleared household.

[0073] It is understandable that the specific parameter thresholds of the above rules can be adjusted by business management personnel according to actual conditions.

[0074] For the rules derived from business experience and data analysis, on the one hand, we can summarize them from the anomalies found in daily business feedback and report monitoring, extract common problems and form rules; on the other hand, we can use machine learning algorithms such as decision trees to find out the features and corresponding thresholds that can provide more information for risk warnings.

[0075] S120. If it is in compliance, determining the customer group to which the declared information belongs based on the risk characteristics included in the declared information.

[0076] Among them, if the risk rules are met, the customer group to which the declared information belongs can be determined based on the risk characteristics included in the declared information. The distribution of applicant customers is composed of multiple customer groups with different risk characteristics. These sub-customer groups are separated in the risk assessment stage to facilitate more accurate judgments later.

[0077] In this solution, optionally, determining the customer group to which the declared information belongs based on the risk characteristics included in the declared information includes:

[0078] Obtain the risk characteristic dimensions included in the declared information;

[0079] If the risk characteristic dimension includes a target dimension, the customer group to which the declared information belongs is determined based on the risk characteristic value of the target dimension.

[0080] There can be many risk feature dimensions. If the dimension of division includes the target dimension, the customer groups can be divided according to the different values ​​of the target dimension. The target dimension can be one or more. For example, if the target dimension includes the house transaction price, the division can be based on the high or low house transaction price. If the target dimension includes the mortgage period of the loan, the division can be based on the length of the mortgage period. Through such a setting, the division result of the customer group to which the lender belongs can be obtained based on the declared information.

[0081] In this solution, optionally, the target dimensions include city level dimension, purchased house type dimension and transaction price dimension;

[0082] Determine the customer group to which the declared information belongs based on the risk characteristic value of the target dimension, including:

[0083] The customer group to which the declared information belongs is determined based on the risk characteristic values ​​of the target dimensions including the city level dimension, the purchased house type dimension and the transaction price dimension.

[0084] Among them, the city level dimension, the type of house purchased dimension and the transaction price dimension can be the most direct basis for evaluating the house purchasing behavior of the lender. Based on these target characteristics, the lender can be divided into customer groups more accurately.

[0085] In the above technical solution, optionally, the risk characteristic values ​​of the city level dimension include: first-tier cities, second-tier cities and third-tier cities;

[0086] The risk characteristic values ​​of the housing type dimension include: new housing and second-hand housing;

[0087] The risk characteristic values ​​of the transaction price dimension include: higher than the preset price and lower than the preset price.

[0088] Among them, first-tier cities, second-tier cities, and third-tier cities can be determined according to the national city classification standards. New houses and second-hand houses can be determined according to the information of house purchases. Higher than the preset price and lower than the preset price can be determined according to the comparison results with the preset price. Through such settings, a clear division method can be given for the feature values ​​of the target features, thereby improving the consistency of the customer group division results.

[0089] In the above technical solution, optionally, the preset price is determined according to the city level dimension and the house type dimension. For example, if the house currently purchased by the borrower is in Shanghai, the city level is level one, and the preset price can be relatively high, such as RMB 10 million. If it is in Harbin, the city level is level two, and the preset price can be relatively low, such as RMB 1.5 million. Thus, different preset prices can be determined according to different city levels, so that the preset price can correspond to the current city level.

[0090] In the above technical solution, optionally, if the risk characteristic value of the city level dimension is a third-tier city, then: determine the customer group to which the declared information belongs based on the risk characteristic value of the house purchase type dimension.

[0091] It is understandable that if it is a third-tier city, the target features can be determined only as the city level and house type, so that there is no need to divide the transaction price, thereby avoiding the large difference in consumption levels between third-tier cities, resulting in the customer segmentation results being unable to truly reflect the lender's loan risk.

[0092] Taking into account stability, differentiation, and interpretability, customers are segmented according to three dimensions: region, house transaction price, and whether it is a new house. According to the performance of customer risk characteristics, a risk control model is established for each customer group. The specific level division can be shown in the following table:

[0093]

[0094] It is understandable that different customer groups can be distinguished by different tags. In the subsequent processing, the model to be selected can be determined by simply obtaining the tag of the customer group.

[0095] S130: Perform risk assessment using a pre-approval risk control model associated with the customer group.

[0096] The relationship between the customer group and the pre-approval risk control model can be predetermined. After the customer group is determined, the corresponding pre-approval risk control model can be used to perform risk assessment. The result of the risk assessment can be two classification results of risk or no risk, or multiple risk levels.

[0097] The pre-approval risk control model uses the lightGBM model. GBDT (Gradient Boosting DecisionTree) is a classic model in machine learning. Its main idea is to use weak classifiers (decision trees) for iterative training to obtain the optimal model. This model has the advantages of good training effect and low overfitting. GBDT is not only widely used in the industry, but is also commonly used for multi-classification, click-through rate prediction, search ranking and other tasks. It is also a deadly weapon in various data mining competitions. According to statistics, more than half of the champion solutions in Kaggle competitions are based on GBDT. LightGBM (Light GradientBoosting Machine) is a framework for implementing the GBDT algorithm. It supports efficient parallel training and has the advantages of faster training speed, lower memory consumption, better accuracy, and support for distributed processing of massive data.

[0098] Common machine learning algorithms, such as neural networks, can be trained in mini-batch mode, and the size of the training data is not limited by memory. However, GBDT needs to traverse the entire training data multiple times in each iteration. If the entire training data is loaded into memory, the size of the training data will be limited; if it is not loaded into memory, repeatedly reading and writing the training data will consume a lot of time. In particular, when faced with massive industrial-level data, ordinary GBDT algorithms cannot meet its needs.

[0099] The main reason for proposing LightGBM is to solve the problems encountered by GBDT in massive data, so that GBDT can be used in industrial practice better and faster.

[0100] S140. If the risk assessment result is passed, the declared information is scored using a preset scoring card to obtain the result of online pre-approval.

[0101] If the risk assessment result is passed, a predetermined score card can be used to score the declared information. It can be understood that the score card is a model commonly used in the financial field to score risk levels.

[0102] In this solution, optionally, a preset scoring card is used to score the declared information to obtain the result of online pre-approval, including:

[0103] The declared information is scored using a preset scoring card, and if the scoring result is higher than a first threshold value, online approval recommendation information is generated.

[0104] Among them, the full score can be 500 points, and the first threshold value can be 400 points. It can be understood that the higher than here can also include the equal to situation, or the threshold value can be set to a decimal, such as 399.5, so that after obtaining the integer scoring result, all possibilities can be fully covered.

[0105] Here, if the score during the pre-approval process is above 400 points, the online approval recommendation information can be directly generated. The recommendation information can be sent to the account manager or the lender for the account manager to confirm and execute the corresponding process.

[0106] On the basis of the above technical solution, optionally, the method further includes:

[0107] If the scoring result is lower than the first threshold value and higher than the second threshold value, the declared information is determined to be low-risk information, and offline approval recommendation information is generated; wherein the second threshold value is lower than the first threshold value.

[0108] The second threshold value can be 200 points. If the score is lower than 400 points and higher than 200 points, it can be determined as low risk and the offline approval process is recommended. The advantage of this setting is that the means and severity adopted in the subsequent approval process can be determined, and then the approval resources can be deployed to achieve reasonable allocation of resources.

[0109] On the basis of the above technical solution, optionally, the method further includes:

[0110] If the scoring result is lower than the second threshold value, the declared information is determined to be high-risk information, and offline approval recommendation information is generated.

[0111] When the score is lower than 200 points, the declared information can be identified as high-risk and offline approval can be adopted, so that more approval resources can be allocated to it to ensure the security of the loan.

[0112] The technical solution provided in the embodiment of the present application obtains the lender's declaration information and executes the preset risk rules to determine whether the declaration information meets the rule standards; if it does, the customer group to which the declaration information belongs is determined based on the risk characteristics included in the declaration information; a pre-approval risk control model associated with the customer group is used to perform risk assessment; if the risk assessment result is passed, the declaration information is scored using a preset scoring card to obtain the result of online pre-approval. The technical solution provided in the present application can adopt different pre-approval methods for different customer groups to achieve the purpose of quickly and accurately pre-approving mortgage loans.

[0113] Figure 2 is a schematic diagram of another online pre-approval method for mortgage provided in an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps:

[0114] The first step is to query the customer's internal and external data and execute the risk rule set. After the customer enters simple information in the mobile banking client and confirms that the customer is eligible to buy a house, the bank's internal information, credit data and other external information of the lender and co-lenders will be queried with the customer's authorization, and the risk rule set will be executed. Customers who do not meet the rule conditions will be notified of the rejection result or transferred to the offline supplementary materials to continue the application.

[0115] The second step is to divide the customers who pass the risk rules. Usually, our application customers are composed of multiple customer groups with different risk characteristics. These sub-customer groups are separated in the risk assessment stage to facilitate more accurate judgments later.

[0116] In the third step, different customer groups use different pre-approval risk control models for risk assessment. In the model development stage, training models for different customer groups separately can enable machine learning models to learn customer risk characteristics more specifically. In this step, the risk of customers is assessed through the model and the data obtained previously. Customers with low risks continue with the subsequent process, while other customers will be informed of the rejection result or transfer to offline supplementary materials to continue the application.

[0117] The fourth step is to carry out the follow-up process and run the existing scorecard. Customers who have passed the pre-approval risk control model will carry out the follow-up process. Customers who have passed the aforementioned risk control model will carry out the follow-up application process and continue to score customers with the existing scorecard. The new risk control model is trained and verified based on three dimensions: city level, whether it is a new house, and transaction price. There are obvious differences in the qualifications, repayment performance, and behavioral performance of customers in different customer groups. Scoring customers by customer group makes the scoring model more targeted and more accurate in obtaining the customer's comprehensive score than the existing scorecard.

[0118] Compared with the original mortgage model, this solution uses the same set of scoring cards for all applicants. In fact, mortgage customers are composed of customers at different levels, and customers at each level have different risk performance and characteristics. The present invention combines business explainability and customer behavior to find out the three dimensions of city level, whether it is a new house, and house transaction price to stratify mortgage customers. Compared with the original model that treats all mortgage customers as a whole, stratifying customers according to this method is more conducive to targeted modeling and strategy formulation.

[0119] Moreover, based on the original mortgage scoring card model, a pre-approval risk control model is deployed in the early stage of the application process. Compared with the traditional one-model approach, it can quickly complete the risk pre-assessment of customers, and provide early warnings and follow-up process guidance. It shortens the loan application life cycle, effectively reduces the time cost of customers waiting, and improves customer experience. The specific process includes: data collection, risk assessment, and risk classification by customer group.

[0120] Figure 3 Schematic diagram of the structure of the online pre-approval device for housing loans provided in the embodiment of the present application. Figure 3 As shown, the online pre-approval device for housing loans includes:

[0121] The risk rule review module 310 is used to obtain the lender's declared information and execute the preset risk rules to determine whether the declared information meets the rule standards;

[0122] The customer group determination module 320 is used to determine the customer group to which the declared information belongs according to the risk characteristics included in the declared information if the audit result of the risk rule audit module is compliance;

[0123] A risk assessment module 330, configured to perform risk assessment using a pre-approval risk control model associated with the customer group;

[0124] The scoring module 340 is used to score the declared information using a preset scoring card if the risk assessment result is passed, so as to obtain the result of online pre-approval.

[0125] The above-mentioned product can execute the method provided in the embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0126] The embodiment of the present application further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute an online pre-approval method for a housing loan when executed by a computer processor, the method comprising:

[0127] Obtain the lender's declared information and execute the preset risk rules to determine whether the declared information meets the rule standards;

[0128] If it is in compliance, the customer group to which the declared information belongs is determined based on the risk characteristics included in the declared information;

[0129] Perform risk assessment using a pre-approval risk control model associated with the customer group;

[0130] If the risk assessment result is passed, the preset score card will be used to score the declared information to obtain the result of online pre-approval.

[0131] Storage medium - any of various types of memory electronic devices or storage electronic devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system, which is connected to the computer system via a network (such as the Internet). The second computer system can provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different unknowns (for example, in different computer systems connected by a network). The storage medium may store program instructions (for example, embodied as a computer program) that can be executed by one or more processors.

[0132] Of course, the storage medium containing computer executable instructions provided in the embodiments of the present application is not limited to the online pre-approval operation of the mortgage as described above, but can also execute related operations in the online pre-approval method for the mortgage provided in any embodiment of the present application.

[0133] An embodiment of the present application provides an electronic device, into which the online pre-approval device for housing loans provided by the embodiment of the present application can be integrated. Figure 4 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown, this embodiment provides an electronic device 400, which includes: one or more processors 420; a storage device 410, which is used to store one or more programs. When the one or more programs are executed by the one or more processors 420, the one or more processors 420 implement the online pre-approval method for housing loans provided in the embodiment of the present application, and the method includes:

[0134] Obtain the lender's declared information and execute the preset risk rules to determine whether the declared information meets the rule standards;

[0135] If it is in compliance, the customer group to which the declared information belongs is determined based on the risk characteristics included in the declared information;

[0136] Perform risk assessment using a pre-approval risk control model associated with the customer group;

[0137] If the risk assessment result is passed, the preset score card will be used to score the declared information to obtain the result of online pre-approval.

[0138] Of course, those skilled in the art will appreciate that the processor 420 also implements the technical solution of the online pre-approval method for housing loans provided in any embodiment of the present application.

[0139] Figure 4 The electronic device 400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0140] like Figure 4 As shown, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of the processor 420 in the electronic device can be one or more. Figure 4 A processor 420 is taken as an example; the processor 420, the storage device 410, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 4 The connection via bus 450 is taken as an example.

[0141] The storage device 410, as a computer-readable storage medium, can be used to store software programs, computer executable programs and module units, such as program instructions corresponding to the online pre-approval method for mortgage loans in the embodiment of the present application.

[0142] The storage device 410 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 according to the use of the terminal, etc. In addition, the storage device 410 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 storage device 410 may further include a memory remotely arranged relative to the processor 420, and these remote memories may be connected 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.

[0143] The input device 430 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 440 may include electronic devices such as a display screen and a speaker.

[0144] The electronic device provided in the embodiment of the present application can adopt different pre-approval methods for different customer groups to achieve the purpose of fast and accurate pre-approval of housing loans.

[0145] The online pre-approval device, storage medium, and electronic device for housing loans provided in the above embodiments can execute the online pre-approval method for housing loans 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 online pre-approval method for housing loans provided in any embodiment of the present application.

[0146] 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 described 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. An online pre-approval method for housing loans, characterized in that: The method comprises: Obtain the lender's declared information, and execute the preset risk rules to determine whether the declared information meets the rule standards, the declared information includes at least one of customer information, liability information and asset information; wherein the customer information includes basic information and behavior information, the liability information includes credit card information and loan information, and the asset information includes investment information, financial information, deposit information, agency payment information and insurance information; the preset risk rules are strategy rules generated based on business experience and data analysis, which are used to inform the customer whether the basic access conditions are met and generate prompts; the basic access conditions include whether the lender's documents are complete and whether the information is authentic; the rule content is set based on the customer hitting the bank's blacklist, the product access conditions that can be judged by the system, and the rules obtained from business experience and data analysis; If it is in compliance, the customer group to which the declared information belongs will be determined based on the risk characteristics included in the declared information; if it is not in compliance, the lender will be notified to provide additional information offline; Perform risk assessment using a pre-approval risk control model associated with the customer group; If the risk assessment result is passed, the application information will be scored using a preset scorecard to obtain the result of online pre-approval; Before executing the preset risk rules to determine whether the declared information meets the rule standards, the method further includes: Determine whether there are any co-lenders; If yes, obtain the loan information of the loan co-lender; Accordingly, the preset risk rules are executed to determine whether the declared information meets the rule standards, including: Execute preset risk rules on the declared information of the lender and the participating information of the participating lender to determine whether the declared information meets the rule standards; Determining the customer group to which the declared information belongs based on the risk characteristics included in the declared information includes: Obtain the risk characteristic dimensions included in the declared information; If the risk characteristic dimension includes a target dimension, the customer group to which the declared information belongs is determined according to the risk characteristic value of the target dimension; The target dimensions include city level, purchased house type and transaction price; The determining the customer group to which the declared information belongs according to the risk characteristic value of the target dimension includes: The customer group to which the declared information belongs is determined according to the risk characteristic values ​​of the target dimensions including city level dimension, house purchase type dimension and transaction price dimension; the risk characteristic values ​​of the city level dimension include: first-tier cities, second-tier cities and third-tier cities; the risk characteristic values ​​of the house purchase type dimension include: new houses and second-hand houses; the risk characteristic values ​​of the transaction price dimension include: higher than a preset price and lower than a preset price; wherein the first-tier cities, second-tier cities and third-tier cities are determined according to the national city classification standards, the new houses and second-hand houses are determined according to the information of house purchases, and the higher than the preset price and lower than the preset price are determined according to the comparison result with the preset price.

2. The method according to claim 1, characterized in that The preset price is determined based on the city level dimension and the purchased house type dimension.

3. The method according to claim 1, characterized in that If the risk characteristic of the city level dimension is a third-tier city, then: The customer group to which the declared information belongs is determined based on the risk characteristic values ​​of the housing purchase type dimension.

4. The method according to claim 1, characterized in that: The application information is scored using a preset scorecard to obtain the online pre-approval results, including: The declared information is scored using a preset scoring card, and if the scoring result is higher than a first threshold value, online approval recommendation information is generated.

5. The method according to claim 4, characterized in that The method further comprises: If the scoring result is lower than the first threshold value and higher than the second threshold value, the declared information is determined to be low-risk information, and offline approval recommendation information is generated; wherein the second threshold value is lower than the first threshold value.

6. The method according to claim 5, characterized in that The method further comprises: If the scoring result is lower than the second threshold value, the declared information is determined to be high-risk information, and offline approval recommendation information is generated.

7. An online pre-approval device for housing loans, characterized in that: The device comprises: The risk rule review module is used to obtain the lender's declared information and execute the preset risk rules to determine whether the declared information meets the rule standards. The declared information includes at least one of customer information, liability information and asset information; wherein the customer information includes basic information and behavior information, the liability information includes credit card information and loan information, and the asset information includes investment information, financial information, deposit information, agency payment information and insurance information; the preset risk rules are strategy rules generated based on business experience and data analysis, which are used to inform customers whether they meet the basic access conditions and generate prompts; the basic access conditions include whether the lender's documents are complete and whether the information is authentic; the rule content is set based on the customer hitting the bank's blacklist, the product access conditions that can be judged by the system, and the rules obtained from business experience and data analysis; A customer group determination module is used to determine the customer group to which the declared information belongs based on the risk characteristics included in the declared information if the audit result of the risk rule audit module is in compliance; if it is not in compliance, the lender is notified to provide additional information offline; A risk assessment module, configured to perform risk assessment using a pre-approval risk control model associated with the customer group; A scoring module is used to score the application information using a preset scoring card if the risk assessment result is passed, so as to obtain the result of online pre-approval; The co-lender information determination module is used to determine whether there is a co-lender before executing the preset risk rules to determine whether the declared information meets the rule standards; if so, obtain the co-lender's loan information; Accordingly, the risk rule review module is specifically used to execute preset risk rules on the application information of the lender and the loan information of the co-lender to determine whether the application information meets the rule standards; The customer group determination module is specifically used to obtain the risk characteristic dimensions included in the declared information; If the risk characteristic dimension includes a target dimension, the customer group to which the declared information belongs is determined according to the risk characteristic value of the target dimension; The target dimensions include city level, purchased house type and transaction price; The customer group to which the declared information belongs is determined according to the risk characteristic values ​​of the target dimensions including city level dimension, house purchase type dimension and transaction price dimension; the risk characteristic values ​​of the city level dimension include: first-tier cities, second-tier cities and third-tier cities; the risk characteristic values ​​of the house purchase type dimension include: new houses and second-hand houses; the risk characteristic values ​​of the transaction price dimension include: higher than a preset price and lower than a preset price; wherein the first-tier cities, second-tier cities and third-tier cities are determined according to the national city classification standards, the new houses and second-hand houses are determined according to the information of house purchases, and the higher than the preset price and lower than the preset price are determined according to the comparison result with the preset price.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, an online pre-approval method for a housing loan as described in any one of claims 1 to 6 is implemented.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the online pre-approval method for housing loan according to any one of claims 1-6 is implemented.

Images