Customer income prediction method, device and medium based on financial information

Abstract

The present disclosure relates to a method, device and medium for predicting customer income based on financial information. The method comprises: obtaining product attributes of a financial product used by a customer and loan information of the customer under the financial product; determining the customer category of the customer according to the product attributes; and inputting the loan information into an income prediction model matching the customer category to determine the income of the customer.

Description

Technical Field

[0001] The present disclosure relates to the field of information technology, and in particular to a method, device and medium for predicting customer income based on financial information. Background Art

[0002] As business develops, more and more financial scenarios, such as credit scenarios, require the prediction of customer income. In related technologies, customer income can be predicted through external data such as tax data, provident fund data, and social security data, or based on customer self-filled data and customized weights. However, external data is difficult to obtain, making it difficult to predict customer income. Both customer self-filled data and customized weights may be inaccurate, resulting in inaccurate final prediction of customer income. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a method, device and medium for predicting customer income based on financial information.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for predicting customer income based on financial information is provided, comprising: Obtaining product attributes of financial products used by customers, as well as loan information of the customers under the financial products; determining a customer category of the customer according to the product attributes; The loan information is input into an income prediction model that matches the customer category to determine the customer's income.

[0005] Optionally, the customer category includes a first category of customers, the first category of customers are customers with at least one first mortgage, the loan information includes a first mortgage monthly payment of each first mortgage in the at least one first mortgage, and the first mortgage is an outstanding mortgage; The revenue prediction model determines the revenue of the customer according to: For each of the first mortgage loans, determine the first income corresponding to each of the first mortgage loans according to the first mortgage monthly payment, the first multiple, and the first coefficient of the first mortgage loan, wherein the first coefficient is determined according to the repayment progress of the first mortgage loan; The income of the customer is determined according to the first income corresponding to each first mortgage loan.

[0006] Optionally, the customer category includes a second category of customers, the second category of customers are customers with at least one second mortgage, the loan information includes the borrowing amount of each second mortgage in the at least one second mortgage, the number of repayment periods of each second mortgage and the opening date of each second mortgage, and the second mortgage is a settled mortgage; The revenue prediction model determines the revenue of the customer according to: For each of the second mortgage loans, determine the second income corresponding to each of the second mortgage loans according to the loan amount, the number of repayment periods, the second multiple and the second coefficient of the second mortgage loan, wherein the second coefficient is determined according to the difference between the current date and the opening date, and the number of repayment periods; The income of the customer is determined based on the second income corresponding to each of the second mortgage loans.

[0007] Optionally, the customer category includes a third category of customers, the third category of customers are customers with a first credit loan and other loans, the loan information includes the usage limit of a credit card corresponding to the first credit loan within a preset time period, the credit limit of the credit card, the loan limit of the other loans, and the loan balance of the other loans, and the other loans are any loans other than credit loans; The revenue prediction model determines the revenue of the customer according to: Determining a first credit limit utilization rate of the credit card according to the usage limit of the credit card corresponding to the first credit loan and the credit limit within the preset time period; Determine a second loan amount utilization rate of the other loan according to the loan balance and the loan amount; Determining a third credit limit usage rate according to the first credit limit usage rate, a first weight matching the first credit limit usage rate, the second credit limit usage rate, and a second weight matching the second credit limit usage rate; The income of the customer is determined based on the third credit limit utilization rate, the credit limit and the loan limit.

[0008] Optionally, determining the first credit limit utilization rate of the credit card according to the usage limit of the credit card corresponding to the first credit loan within the preset time period and the credit limit includes: Determining an average usage limit of the credit card according to the usage limit of the credit card corresponding to the first credit loan within the preset time period; According to a first ratio between the average credit limit used and the credit limit, a comparison is made with a preset value, and a first minimum value between the first ratio and the preset value is determined as the first credit limit utilization rate; The determining the second loan amount utilization rate of the other loan according to the loan balance and the loan amount includes: A second ratio between the loan balance and the loan amount is compared with the preset value, and a second minimum value between the second ratio and the preset value is determined as a second amount utilization rate.

[0009] Optionally, the customer category includes a fourth category of customers, the fourth category of customers are customers with revolving loans, and the loan information includes: a first maximum credit limit of the revolving loan, a minimum repayment ratio of the revolving loan, and the number of installments of the revolving loan; The revenue prediction model determines the revenue of the customer according to: Determining a third ratio according to a ratio between a preset value and the number of installments; The income of the customer is determined based on the first maximum credit line, the minimum repayment ratio and the third ratio.

[0010] Optionally, the customer category includes a fifth category of customers, the fifth category of customers being customers with a second credit loan, and the loan information includes: a second maximum credit limit of each credit card in at least one credit card corresponding to the second credit loan, and a minimum credit card repayment limit; The revenue prediction model determines the revenue of the customer according to: The income of the customer is determined based on the maximum value of the second maximum credit limit of the at least one credit card and the minimum repayment amount.

[0011] According to a second aspect of an embodiment of the present disclosure, there is provided a device for predicting customer income based on financial information, comprising: An acquisition module, configured to acquire product attributes of a financial product used by a customer, and loan information of the customer under the financial product; A first determination module is configured to determine a customer category of the customer according to the product attributes; The second determination module is configured to input the loan information into an income prediction model matching the customer category to determine the customer's income.

[0012] According to a third aspect of an embodiment of the present disclosure, there is provided a device for predicting customer income based on financial information, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Obtaining product attributes of financial products used by customers, as well as loan information of the customers under the financial products; determining a customer category of the customer according to the product attributes; The loan information is input into an income prediction model that matches the customer category to determine the customer's income.

[0013] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the customer income prediction method based on financial information provided in the first aspect of the present disclosure are implemented.

[0014] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: determining a customer's income through loan information, and using the customer's liabilities to reversely predict the customer's income. Since loan information is easy to obtain, the problem of difficulty in obtaining external data in the process of customer income prediction is avoided. In addition, the customer's income is determined using an income prediction model that matches the customer category. Different customer categories use different income prediction methods, which allows for more targeted income predictions and can improve the accuracy of predicted customer income.

[0015] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0017] Figure 1 The present invention is a flowchart of a method for predicting customer income based on financial information according to an exemplary embodiment.

[0018] Figure 2 The invention is a flow chart of determining the income of the first type of customers according to the prediction model shown in an exemplary embodiment.

[0019] Figure 3 The figure is a flow chart of determining the income of the second type of customers according to the prediction model shown in an exemplary embodiment.

[0020] Figure 4 The figure is a flow chart of determining the income of the third type of customers according to the prediction model shown in an exemplary embodiment.

[0021] Figure 5 The figure is a flow chart of determining the income of the fourth category of customers according to a prediction model shown in an exemplary embodiment.

[0022] Figure 6 The figure is a flow chart of determining the income of the fifth category of customers according to a prediction model shown in an exemplary embodiment.

[0023] Figure 7 The invention is a block diagram showing a device for predicting customer income based on financial information according to an exemplary embodiment.

[0024] Figure 8The invention is a block diagram showing a device for predicting customer income based on financial information according to an exemplary embodiment.

[0025] Fig. 9 The invention is a block diagram showing a device for predicting customer income based on financial information according to an exemplary embodiment. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0027] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0028] As mentioned in the background technology, in the related art, it is possible to predict the income of customers through external data such as tax data, provident fund data, and social security data, or to predict the income of customers based on the data filled in by customers and customized weights. However, it is difficult to obtain external data, which makes it difficult to predict the income of customers. Both the data filled in by customers and the customized weights may be inaccurate, resulting in inaccurate final prediction of the income of customers.

[0029] The external data in the related technologies do not cover a large area or a large proportion of the population, and are personal privacy data that is difficult to obtain. In addition, the custom weights in the related technologies can be set based on experience, which is highly subjective and cannot be objectively quantified to be correct. This brings great trouble to judging the actual income of customers, resulting in inaccurate final prediction of customer income.

[0030] To this end, the present disclosure proposes a method, device and medium for predicting customer income based on financial information.

[0031] Figure 1 is a flow chart of a method for predicting customer income based on financial information according to an exemplary embodiment. Figure 1 As shown, the customer income prediction method based on financial information may include the following steps 110-130.

[0032] Step 110, obtaining product attributes of the financial product used by the customer and the customer's loan information under the financial product.

[0033] In some embodiments, obtaining product attributes of a financial product used by a customer and the customer's loan information under the financial product may include: obtaining product attributes of the financial product used by the customer and the customer's loan information under the financial product based on historical credit data in the People's Bank of China's credit report.

[0034] The disclosed embodiment obtains product attributes and loan information through the credit report of the People's Bank of China. Since the credit report of the People's Bank of China has a high coverage, it can fully cover the credit population in various regions and the customer base, without worrying about the inability to predict customer income due to regional or customer differences.

[0035] Step 120, determining the customer category of the customer based on the product attributes.

[0036] In some embodiments, financial products may include loan products, and different loan products may have different product attributes. In some embodiments, customer categories may include at least one of the following: first-category customers, second-category customers, third-category customers, fourth-category customers, fifth-category customers, and sixth-category customers, wherein the first-category customers are customers with at least one first mortgage, which is an outstanding mortgage; the second-category customers are customers with at least one second mortgage, which is a settled mortgage; the third-category customers are customers with a first credit loan and other loans, which are any loans other than credit loans; the fourth-category customers are customers with revolving loans; the fifth-category customers are customers with a second credit loan; and the sixth-category customers are customers with other loans.

[0037] In some embodiments, the credit loan may include a credit card loan, and the third type of customer may be a customer who has both a credit card loan and other loans. The fourth type of customer may be a customer who only has a credit card loan.

[0038] Step 130, input the loan information into an income prediction model that matches the customer category to determine the customer's income.

[0039] In some embodiments, the loan information corresponding to different customer categories is different. The loan information of the first category of customers includes the monthly payment of the first mortgage of each first mortgage in at least one first mortgage. The loan information of the second category of customers includes the borrowing amount of each second mortgage in at least one second mortgage, the number of repayment periods of each second mortgage, and the opening date of each second mortgage. The loan information of the third category of customers includes the usage limit of the credit card corresponding to the first credit loan within a preset time period, the credit limit of the credit card, the loan limit of other loans, and the loan balance of other loans. The loan information of the fourth category of customers includes: the first maximum credit limit of the revolving loan, the minimum repayment ratio of the revolving loan, and the number of installments of the revolving loan. The loan information of the fifth category of customers includes: the second maximum credit limit of each credit card in at least one credit card corresponding to the second credit loan, and the minimum repayment limit of the credit card. The loan information of the sixth category of customers includes the monthly payment of each other loan in at least one other loan.

[0040] In some embodiments, the income prediction model can determine the income of customers according to the loan information of customers of different customer categories in different ways. The income prediction model can be a pre-trained machine learning model, and the pre-trained income prediction model can be obtained by supervised learning training based on sample data with labels. The label can represent the income of the labeled customer, and the sample data can include sample loan information. For supervised learning training, please refer to the relevant technology, which will not be repeated here.

[0041] In some embodiments, each customer category corresponds to an income prediction model, and accordingly, when each income prediction model is trained, the sample data may include sample loan information of customers of one category. In some embodiments, multiple customer categories correspond to an income prediction model, and accordingly, when the income prediction model is trained, the sample data may be sequence information, each element in the sequence information represents sample loan information of customers of the corresponding category, and each element is annotated with a label, and the label represents the income of customers of the corresponding category.

[0042] The disclosed embodiment trains one revenue prediction model for each customer category, and each revenue prediction model has less sample data, which can improve the training efficiency of each revenue prediction model. In addition, the disclosed embodiment trains one revenue prediction model for multiple customer categories, and when the revenue prediction model is applied, only one model needs to be called to realize revenue prediction for multiple customer categories, which can improve the prediction efficiency.

[0043] For details on how the revenue forecasting model determines the revenue from the first to fifth categories of customers, please refer to the following: Figure 2-6 And the related description will not be repeated here.

[0044] The disclosed embodiment determines a customer's income through loan information, and uses the customer's liabilities to reversely predict the customer's income. Since loan information is easy to obtain, the problem of difficulty in obtaining external data in the process of customer income prediction is avoided. The customer's income is determined using an income prediction model that matches the customer category. Different customer categories use different income prediction methods, which allows for more targeted income predictions and can improve the accuracy of predicted customer income.

[0045] In some embodiments, the customer categories include a sixth category of customers, and the loan information includes the monthly payment of each other loan in at least one other loan; the income prediction model determines the customer's income in the following manner: determining the total monthly payment based on the monthly payment of each other loan, and determining the total monthly payment as the customer's income.

[0046] In some embodiments, when the customer does not use financial products, the customer's income is determined based on the preset income. When the customer does not use financial products, it can be characterized that the customer does not have any loans and the customer category is a white household. In this case, the preset income can be determined as the customer's income. The preset income can be a preset fixed minimum income.

[0047] It is worth noting that a customer can include multiple customers, and multiple customers can correspond to different or the same customer categories. Figure 2-6 Any of the processes for determining a customer's revenue can exist independently, or Figure 2-6 Multiple processes for determining a customer's revenue can exist simultaneously.

[0048] Figure 2 FIG. 1 is a flow chart of determining the income of the first type of customers according to a prediction model shown in an exemplary embodiment. Figure 2 As shown, the process may include the following steps 210 and 220 .

[0049] Step 210, for each first mortgage, determine the first income corresponding to each first mortgage according to the first mortgage monthly payment, the first multiple and the first coefficient of the first mortgage, where the first coefficient is determined according to the repayment progress of the first mortgage.

[0050] In some embodiments, the first mortgage may include multiple types. For example, the first mortgage may include at least one of the following loans whose account status is outstanding or not transferred out: personal commercial housing loan, personal commercial housing loan and personal housing provident fund loan.

[0051] In some embodiments, the first mortgage monthly payment can be determined based on the second mortgage monthly payment and the third mortgage monthly payment. The second mortgage monthly payment can be the mortgage monthly payment determined based on the credit report of the People's Bank of China, and the third mortgage monthly payment can be the mortgage monthly payment calculated based on the total mortgage amount in equal installments of principal and interest.

[0052] In some embodiments, the first mortgage monthly payment can be the maximum or minimum of the second mortgage monthly payment and the third mortgage monthly payment.

[0053] Because the information from the People's Bank of China may not be consistent with the actual monthly payment, the disclosed embodiment ensures that the monthly payment of the first mortgage is more in line with the customer's actual monthly payment by comparing the second mortgage monthly payment with the third mortgage monthly payment, that is, comparing the mortgage monthly payment in the People's Bank of China information with the equal principal and interest monthly payment calculated based on the loan amount and number of periods, thereby avoiding the situation where the customer's income is subsequently determined to be inaccurate.

[0054] In some embodiments, the third mortgage monthly payment can be calculated according to the following method: Third mortgage monthly payment = repayment period number loan amount Equal principal and interest coefficient. The equal principal and interest coefficient is calculated by assigning a specified interest rate through the equal principal and interest calculation formula.

[0055] For example, the monthly payment of the third mortgage can be determined according to the following formula (1):

[0056] Among them, M represents the monthly payment of the third mortgage, P represents the loan amount, r represents the monthly interest rate, and N represents the number of repayment periods.

[0057] In some embodiments, if the loan term of the first mortgage exceeds the preset term, the monthly payment of the third mortgage = the monthly payment of equal principal and interest The house price increase coefficient can be determined based on the average increase in house prices within a preset period of time, and the equal principal and interest monthly payment can be the monthly payment determined based on formula (1).

[0058] In the embodiment of the present disclosure, when the loan term exceeds the preset term, a house price increase coefficient is introduced to determine the monthly payment of the third mortgage loan, taking into account the actual changes in the housing market, that is, the changes in house prices. The estimated monthly payment of the third mortgage loan can better reflect the customer's actual wealth appreciation, and the appropriate supplementation of the house price increase is helpful to more accurately estimate the customer's repayment ability and improve the accuracy of the customer's income.

[0059] In some embodiments, the repayment progress may be obtained based on the number of mortgage periods paid / the total number of mortgage periods, or may be obtained based on (the number of repayment periods-the number of remaining repayment periods) / the number of repayment periods.

[0060] In some embodiments, the first income may be determined according to the following method: first income = first mortgage monthly payment First multiple The first target coefficient may be determined based on the first coefficient. For example, the first target coefficient may be the same as the first coefficient, or greater than the first coefficient. The first coefficient may be the same as the repayment progress. For the calculation method of the repayment progress, please refer to the above description, which will not be repeated here. The first multiple may be determined based on actual needs. For example, the first multiple may be 1.5 or 2, etc.

[0061] The repayment progress of the disclosed embodiment can reflect the portion of the mortgage that the customer has repaid, reflecting the customer's performance of the loan. Therefore, the first income not only depends on the loan balance, but also takes into account the progress of loan repayment, making the first income more real and accurate. For example, if the value of the repayment progress is larger, it means that the customer has repaid more, which can indirectly reflect that the customer's financial situation is relatively loose, so that the estimated first income can be more in line with the customer's financial situation.

[0062] Step 220, determining the customer's income based on the first income corresponding to each first mortgage loan.

[0063] In some embodiments, determining the income of a customer based on the first income corresponding to each first mortgage loan may include: determining the total of the first incomes by summing the first incomes corresponding to each first mortgage loan; and determining the total of the first incomes as the income of the customer.

[0064] According to regulatory requirements, banks and lending institutions need to ensure that customers have sufficient repayment capacity. When determining the income of the first type of customers, the disclosed embodiment comprehensively considers the customer's loan situation, repayment progress, property appreciation, and the first income of various first mortgage loans (i.e., the situation of different loan accounts), making the customer income estimation more comprehensive and accurate, in line with the strict requirements of supervision. Through more accurate income estimation, the risk of default is effectively reduced, the risk control capability is enhanced, and the accuracy and security of related business approvals (e.g., loan approvals) are improved.

[0065] Figure 3 FIG. 4 is a flowchart of determining the income of the second type of customers according to a prediction model shown in an exemplary embodiment. Figure 3 As shown, the process may include the following steps 310 and 320 .

[0066] Step 310, for each second mortgage, determine the second income corresponding to each second mortgage according to the loan amount, the number of repayment periods, the second multiple and the second coefficient of the second mortgage, where the second coefficient is determined according to the difference between the current date and the opening date, and the number of repayment periods.

[0067] In some embodiments, the second mortgage may include multiple types. For example, the second mortgage may include at least one of the following loans whose account status is settled or transferred out: personal commercial housing loan, personal commercial housing loan and personal housing provident fund loan.

[0068] In some embodiments, the second income can be obtained according to the following method: Second income = (loan amount / repayment period) The second target coefficient is determined according to the second multiple and the second coefficient. For example, the second target coefficient may be the second multiple. The second coefficient, or it can be (V1 + second multiple The second coefficient), V1 can be any value within the preset positive integer range. The preset positive integer range can be specifically determined according to actual needs, and the present disclosure does not impose any restrictions on this. The difference between the current date and the issuance date can represent the number of days of the date difference. The second coefficient can be obtained in the following manner: second coefficient = (current date - issuance date) / number of repayment periods. The second multiple can be specifically determined according to actual needs, for example, the second multiple can be 1.5 or 2.

[0069] Step 320, determining the customer's income based on the second income corresponding to each second mortgage loan.

[0070] In some embodiments, determining the income of the client based on the second income corresponding to each second mortgage loan may include: determining the maximum second income among the second incomes corresponding to each second mortgage loan as the income of the client.

[0071] When determining the income of a mortgage customer who has paid off, the disclosed embodiment not only considers the total amount and number of installments of the loan, but also introduces the date of loan issuance, which can well reflect the customer's historical repayment record and make a reasonable estimate of future income. Among them, the second coefficient can reflect the customer's historical progress and monthly payment situation, and simultaneously consider the customer's current asset burden and past financial behavior, thereby accurately estimating the customer's future income and providing the accuracy of the customer's income.

[0072] Additionally, for customers with multiple second mortgages, by determining the maximum second income, we ensure that the income contribution of all loan accounts is taken into account, thereby avoiding underestimation of the customer's repayment ability.

[0073] In some embodiments, determining the income of a customer based on the second income corresponding to each second mortgage loan may also include: if the loan term of the second mortgage loan exceeds a preset term, determining the income of the customer based on the house price increase coefficient and the maximum second income among the second incomes corresponding to each second mortgage loan. The house price increase coefficient determines the customer's income. The house price increase coefficient can be determined based on the average increase in house prices within a preset number of years.

[0074] In the embodiment of the present disclosure, when the loan term exceeds the preset term, a house price increase coefficient is introduced to determine the income of the second category of customers, taking into account the actual changes in the housing market, that is, the changes in house prices. The estimated customer income can better reflect the customer's actual wealth appreciation. Appropriate supplementation of house price increases helps to more accurately estimate the customer's repayment ability and improve the accuracy of the customer's income.

[0075] Figure 4 FIG. 4 is a flow chart of determining the income of the third type of customers according to a prediction model shown in an exemplary embodiment. Figure 4 As shown, the process may include the following steps 410-440.

[0076] Step 410: Determine a first credit limit utilization rate of the credit card according to the usage limit and the credit limit of the credit card corresponding to the first credit loan within a preset time period.

[0077] The credit limit of a credit card may be the maximum credit amount that can be used within a specific period. The first credit loan may correspond to at least one credit card, and different credit cards may be issued by different card issuers. The credit limits of multiple credit cards may be determined based on the sum of the maximum credit limits of the card issuers of each credit card.

[0078] In some embodiments, the preset time period may be specifically determined according to actual needs. For example, the preset time period may be 6 months or 12 months.

[0079] In some embodiments, determining a first credit limit utilization rate of a credit card according to a usage limit and a credit limit of a credit card corresponding to a first credit loan within a preset time period includes: determining an average usage limit of a credit card according to a usage limit of a credit card corresponding to a first credit loan within a preset time period; A first ratio between the average usage limit and the credit limit is compared with a preset value, and a first minimum value between the first ratio and the preset value is determined as the first limit usage rate.

[0080] In some embodiments, the preset value may be determined according to actual needs, for example, the preset value may be 1. For example, the first credit limit utilization rate may be determined according to the following method: first credit limit utilization rate = min (average credit limit / credit limit, 1).

[0081] Step 420, determining a second loan limit utilization rate of other loans according to the loan balance and the loan limit.

[0082] In some embodiments, determining a second loan amount utilization rate for other loans based on the loan balance and the loan amount includes: comparing a second ratio between the loan balance and the loan amount with a preset value, and determining a second minimum value between the second ratio and the preset value as the second loan amount utilization rate.

[0083] For example, still taking the preset value of 1 as an example, the second credit limit utilization rate can be determined according to the following method: second credit limit utilization rate = min (loan balance / loan limit, 1).

[0084] In some embodiments, when the loan account of the other loan includes multiple ones, the loan amount can be determined according to the sum of the loan amounts of the lending institutions of each loan account. For example, the loan amount = sum (loan amount of each institution), where sum refers to a summation operation.

[0085] Step 430, determining a third credit limit usage rate according to the first credit limit usage rate, the first weight matching the first credit limit usage rate, the second credit limit usage rate, and the second weight matching the second credit limit usage rate.

[0086] In some embodiments, determining the third credit usage rate according to the first credit usage rate, the first weight matching the first credit usage rate, the second credit usage rate, and the second weight matching the second credit usage rate may include: performing a weighted sum operation according to the first credit usage rate, the first weight, the second credit usage rate, and the second weight to determine the third credit usage rate. For example, the third credit usage rate is obtained according to the following method: the third credit usage rate = the first credit usage rate First weight + second quota utilization rate Second weight.

[0087] The first weight and the second weight can be determined according to the actual situation. For example, the weight corresponding to a credit utilization rate of 60% is 0.7, and the weight corresponding to a credit utilization rate of 90% is 0.3. The first weight and the second weight can be adjusted according to different usage situations, indirectly reflecting the actual burden of the customer, making the income estimation more accurate.

[0088] The disclosed embodiment calculates the first credit limit utilization rate and the second credit limit utilization rate, that is, calculates the credit limit utilization rate of each credit card and loan, and determines the third credit limit utilization rate in combination with a weighted method, which can more accurately reflect the customer's burden on both credit cards and other loans, and improve the accuracy of the customer's income. In addition, the weighted credit limit utilization rate calculation method avoids the error that may be caused by a single utilization rate. For example, if the credit card utilization rate is high and the loan utilization rate is low, the setting of weights can help adjust the final income estimate to avoid underestimating or ignoring the loan burden, thereby improving the accuracy of the estimate.

[0089] Step 440, determining the customer's income based on the third credit limit utilization rate, the credit limit, and the loan limit.

[0090] In some embodiments, the income of a customer can be determined as follows: Customer's income = third target coefficient (Credit line + loan line). The third target coefficient may be determined according to the third line utilization rate. For example, the third target coefficient may be the same as the third line utilization rate, or may be less than the third line utilization rate.

[0091] The disclosed embodiment not only takes into account the credit limit and loan limit of the credit card, but also separately incorporates the limit of each card issuing institution and lending institution into the calculation, to ensure that the customer's expenditures on multiple channels are not missed. Through comprehensive calculation, the estimated results of income are more comprehensive, which can accurately reflect the customer's financial status and provide accuracy of income.

[0092] In addition, banks and lending institutions need to ensure that customers have sufficient repayment capacity when issuing credit cards and loans. The disclosed embodiments meet regulatory requirements for income and repayment capacity verification by comprehensively considering credit card and loan limits and their usage, helping institutions reduce default risks and improve risk control capabilities.

[0093] Figure 5 FIG. 4 is a flow chart of determining the income of the fourth type of customers according to a prediction model shown in an exemplary embodiment. Figure 5 As shown, the process may include the following steps 510 and 520.

[0094] Step 510, determining a third ratio based on the ratio between the preset value and the number of installments.

[0095] In some embodiments, the preset value can be specifically determined according to actual needs, for example, the preset value can be 1. For example, the third ratio can be determined in the following manner: the third ratio = 1 / number of installments. In a possible implementation, the number of installments can be specifically determined according to actual needs, for example, the number of installments can be 12 or 16, etc.

[0096] Step 520, determining the customer's income based on the first maximum credit limit, the minimum repayment ratio and the third ratio.

[0097] In some embodiments, determining the income of a customer based on the first maximum credit line, the minimum repayment ratio, and the third ratio may include: performing a product operation based on the first maximum credit line, the minimum repayment ratio, and the third ratio to determine the income of the customer. For example, the income of the customer may be determined in the following manner: Income of the customer = first maximum credit line Minimum repayment ratio The third ratio.

[0098] The minimum repayment ratio can be determined based on actual circumstances. For example, the minimum repayment ratio can be 10%.

[0099] The disclosed embodiment determines the income of the customer based on the first maximum credit line, the minimum repayment ratio and the third ratio, the third ratio is determined by the number of installments, and the number of installments takes into account the repayment period of the customer for the revolving loan product, so as to better match the customer's income with his repayment ability and avoid over-underestimation of the customer's financial situation. And by determining the customer's income in this way, the accuracy of the income can be provided.

[0100] Figure 6 FIG. 4 is a flowchart of determining the income of the fifth category of customers according to a prediction model shown in an exemplary embodiment. Figure 6 As shown, the process may include the following steps 610 .

[0101] Step 610, determining the customer's income based on the maximum value of the second maximum credit limit of at least one credit card and the minimum repayment limit.

[0102] In some embodiments, determining the income of a customer based on the maximum value of the second maximum credit limit of at least one credit card and the minimum repayment amount may include: determining the income of the customer by multiplying the maximum value by the minimum repayment amount.

[0103] Figure 7 is a block diagram of a device for predicting customer income based on financial information according to an exemplary embodiment. Figure 7 , the customer income prediction device 700 based on financial information includes: The acquisition module 710 is configured to acquire product attributes of a financial product used by a customer and loan information of the customer under the financial product; A first determination module 720 is configured to determine a customer category of the customer according to the product attributes; The second determination module 730 is configured to input the loan information into an income prediction model matching the customer category to determine the customer's income.

[0104] Optionally, the customer category includes a first category of customers, the first category of customers are customers with at least one first mortgage, the loan information includes a first mortgage monthly payment of each first mortgage in the at least one first mortgage, and the first mortgage is an outstanding mortgage; The second determining module 730 is further configured to: For each of the first mortgage loans, determine the first income corresponding to each of the first mortgage loans according to the first mortgage monthly payment, the first multiple, and the first coefficient of the first mortgage loan, wherein the first coefficient is determined according to the repayment progress of the first mortgage loan; The income of the customer is determined according to the first income corresponding to each first mortgage loan.

[0105] Optionally, the customer category includes a second category of customers, the second category of customers are customers with at least one second mortgage, the loan information includes the borrowing amount of each second mortgage in the at least one second mortgage, the number of repayment periods of each second mortgage and the opening date of each second mortgage, and the second mortgage is a settled mortgage; The second determining module 730 is further configured to: For each of the second mortgage loans, determine the second income corresponding to each of the second mortgage loans according to the loan amount, the number of repayment periods, the second multiple and the second coefficient of the second mortgage loan, wherein the second coefficient is determined according to the difference between the current date and the opening date, and the number of repayment periods; The income of the customer is determined based on the second income corresponding to each of the second mortgage loans.

[0106] Optionally, the customer category includes a third category of customers, the third category of customers are customers with a first credit loan and other loans, the loan information includes the usage limit of a credit card corresponding to the first credit loan within a preset time period, the credit limit of the credit card, the loan limit of the other loans, and the loan balance of the other loans, and the other loans are any loans other than credit loans; The second determining module 730 is further configured to: Determining a first credit limit utilization rate of the credit card according to the usage limit of the credit card corresponding to the first credit loan and the credit limit within the preset time period; Determine a second loan amount utilization rate of the other loan according to the loan balance and the loan amount; Determining a third credit limit usage rate according to the first credit limit usage rate, a first weight matching the first credit limit usage rate, the second credit limit usage rate, and a second weight matching the second credit limit usage rate; The income of the customer is determined based on the third credit limit utilization rate, the credit limit and the loan limit.

[0107] Optionally, the second determining module 730 is further configured to: Determining an average usage limit of the credit card according to the usage limit of the credit card corresponding to the first credit loan within the preset time period; According to a first ratio between the average credit limit used and the credit limit, a comparison is made with a preset value, and a first minimum value between the first ratio and the preset value is determined as the first credit limit utilization rate; The second determining module 730 is further configured to: A second ratio between the loan balance and the loan amount is compared with the preset value, and a second minimum value between the second ratio and the preset value is determined as a second amount utilization rate.

[0108] Optionally, the customer category includes a fourth category of customers, the fourth category of customers are customers with revolving loans, and the loan information includes: a first maximum credit limit of the revolving loan, a minimum repayment ratio of the revolving loan, and the number of installments of the revolving loan; The second determining module 730 is further configured to: Determining a third ratio according to a ratio between a preset value and the number of installments; The income of the customer is determined based on the first maximum credit line, the minimum repayment ratio and the third ratio.

[0109] Optionally, the customer category includes a fifth category of customers, the fifth category of customers being customers with a second credit loan, and the loan information includes: a second maximum credit limit of each credit card in at least one credit card corresponding to the second credit loan, and a minimum credit card repayment limit; The second determining module 730 is further configured to: The income of the customer is determined based on the maximum value of the second maximum credit limit of the at least one credit card and the minimum repayment amount.

[0110] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0111] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon. When the program instructions are executed by a processor, the steps of the method for predicting customer income based on financial information provided by the present disclosure are implemented.

[0112] Figure 8 8 is a block diagram of a device 800 for predicting customer income based on financial information according to an exemplary embodiment. For example, the device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0113] Reference Figure 8 , the device 800 may include one or more of the following components: a first processing component 802 , a first memory 804 , a first power supply component 806 , a multimedia component 808 , an audio component 810 , a first input / output interface 812 , a sensor component 814 , and a communication component 816 .

[0114] The first processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The first processing component 802 may include one or more first processors 820 to execute instructions to complete all or part of the steps of the above-mentioned customer income prediction method based on financial information. In addition, the first processing component 802 may include one or more modules to facilitate the interaction between the first processing component 802 and other components. For example, the first processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the first processing component 802.

[0115] The first memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The first memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0116] The first power source component 806 provides power to various components of the device 800. The first power source component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 800.

[0117] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0118] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the device 800 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the first memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0119] The first input / output interface 812 provides an interface between the first processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0120] The sensor assembly 814 includes one or more sensors for providing various aspects of the status assessment of the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, and the sensor assembly 814 can also detect the position change of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800, and the temperature change of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0121] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0122] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned customer revenue prediction method based on financial information.

[0123] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a first memory 804 including instructions, and the instructions can be executed by the first processor 820 of the device 800 to complete the above-mentioned customer income prediction method based on financial information. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0124] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above-mentioned customer income prediction method based on financial information when executed by the programmable device.

[0125] Fig. 9 is a block diagram of a device 900 for predicting customer income based on financial information according to an exemplary embodiment. For example, the device 900 may be provided as a server. Fig. 9 The apparatus 900 includes a second processing component 922, which further includes one or more processors, and a memory resource represented by a second memory 932 for storing instructions executable by the second processing component 922, such as an application. The application stored in the second memory 932 may include one or more modules, each corresponding to a set of instructions. In addition, the second processing component 922 is configured to execute instructions to perform the above-mentioned customer income prediction method based on financial information.

[0126] The device 900 may also include a second power supply component 926 configured to perform power management of the device 900, a wired or wireless network interface 950 configured to connect the device 900 to a network, and a second input / output interface 958. The device 900 may operate based on an operating system stored in the memory 932, such as Windows Server 2000. TM , Mac OSX TM , Unix TM , Linux TM , FreeBSD TM or similar.

[0127] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

[0128] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A customer income prediction method based on financial information, characterized in that: include: Obtaining product attributes of financial products used by customers, as well as loan information of the customers under the financial products; determining a customer category of the customer according to the product attributes; The loan information is input into an income prediction model that matches the customer category to determine the customer's income.

2. The method according to claim 1, characterized in that The customer categories include first-category customers, the first-category customers are customers with at least one first mortgage, the loan information includes the first mortgage monthly payment of each first mortgage in the at least one first mortgage, and the first mortgage is an outstanding mortgage; The revenue prediction model determines the revenue of the customer according to: For each of the first mortgage loans, determine the first income corresponding to each of the first mortgage loans according to the first mortgage monthly payment, the first multiple, and the first coefficient of the first mortgage loan, wherein the first coefficient is determined according to the repayment progress of the first mortgage loan; The income of the customer is determined according to the first income corresponding to each first mortgage loan.

3. The method according to claim 1 or 2, characterized in that: The customer category includes a second category of customers, the second category of customers are customers who have at least one second mortgage, the loan information includes the borrowing amount of each second mortgage in the at least one second mortgage, the number of repayment periods of each second mortgage and the opening date of each second mortgage, and the second mortgage is a settled mortgage; The revenue prediction model determines the revenue of the customer according to: For each of the second mortgage loans, determine the second income corresponding to each of the second mortgage loans according to the loan amount, the number of repayment periods, the second multiple and the second coefficient of the second mortgage loan, wherein the second coefficient is determined according to the difference between the current date and the opening date, and the number of repayment periods; The income of the customer is determined based on the second income corresponding to each of the second mortgage loans.

4. The method according to claim 1, characterized in that The customer categories include a third category of customers, the third category of customers are customers with a first credit loan and other loans, the loan information includes the usage limit of the credit card corresponding to the first credit loan within a preset time period, the credit limit of the credit card, the loan limit of the other loan and the loan balance of the other loan, and the other loan is any loan other than a credit loan; The revenue prediction model determines the revenue of the customer according to: Determining a first credit limit utilization rate of the credit card according to the usage limit of the credit card corresponding to the first credit loan and the credit limit within the preset time period; Determine a second loan amount utilization rate of the other loan according to the loan balance and the loan amount; Determining a third credit limit usage rate according to the first credit limit usage rate, a first weight matching the first credit limit usage rate, the second credit limit usage rate, and a second weight matching the second credit limit usage rate; The income of the customer is determined based on the third credit limit utilization rate, the credit limit and the loan limit.

5. The method according to claim 4, characterized in that The determining the first credit limit utilization rate of the credit card according to the usage limit of the credit card corresponding to the first credit loan within the preset time period and the credit limit includes: Determining an average usage limit of the credit card according to the usage limit of the credit card corresponding to the first credit loan within the preset time period; According to a first ratio between the average credit limit used and the credit limit, a comparison is made with a preset value, and a first minimum value between the first ratio and the preset value is determined as the first credit limit utilization rate; The determining the second loan amount utilization rate of the other loan according to the loan balance and the loan amount includes: A second ratio between the loan balance and the loan amount is compared with the preset value, and a second minimum value between the second ratio and the preset value is determined as a second amount utilization rate.

6. The method according to claim 1, characterized in that The customer category includes a fourth category of customers, the fourth category of customers are customers with revolving loans, and the loan information includes: a first maximum credit limit of the revolving loan, a minimum repayment ratio of the revolving loan, and the number of installments of the revolving loan; The revenue prediction model determines the revenue of the customer according to: Determining a third ratio according to a ratio between a preset value and the number of installments; The income of the customer is determined based on the first maximum credit line, the minimum repayment ratio and the third ratio.

7. The method according to claim 1, characterized in that The customer categories include a fifth category of customers, the fifth category of customers are customers with a second credit loan, and the loan information includes: a second maximum credit limit of each credit card in at least one credit card corresponding to the second credit loan, and a minimum credit card repayment limit; The revenue prediction model determines the revenue of the customer according to: The income of the customer is determined based on the maximum value of the second maximum credit limit of the at least one credit card and the minimum repayment amount.

8. A customer income prediction device based on financial information, characterized in that: include: An acquisition module, configured to acquire product attributes of a financial product used by a customer, and loan information of the customer under the financial product; A first determination module is configured to determine a customer category of the customer according to the product attributes; The second determination module is configured to input the loan information into an income prediction model matching the customer category to determine the customer's income.

9. A customer income prediction device based on financial information, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Obtaining product attributes of financial products used by customers, as well as loan information of the customers under the financial products; determining a customer category of the customer according to the product attributes; The loan information is input into an income prediction model that matches the customer category to determine the customer's income.

10. 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 described in any one of claims 1 to 7 are implemented.

Images