CN113962796A - Wind control data processing method and system based on user information and electronic equipment - Google Patents
Wind control data processing method and system based on user information and electronic equipment Download PDFInfo
- Publication number
- CN113962796A CN113962796A CN202111211828.8A CN202111211828A CN113962796A CN 113962796 A CN113962796 A CN 113962796A CN 202111211828 A CN202111211828 A CN 202111211828A CN 113962796 A CN113962796 A CN 113962796A
- Authority
- CN
- China
- Prior art keywords
- user
- rejected
- overdue
- rate
- judgment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Abstract
The disclosure relates to the technical field of computer information processing, in particular to a method, a system and an electronic device for processing wind control data based on user information, wherein the method comprises the following steps: the server acquires user information of a plurality of rejected users after wind control audit; the server determines a first judgment condition influencing the refusal of the refused user, and adjusts the first judgment condition according to a preset step length; the server determines the passing rate of the rejected user after passing according to the user information and the adjusted first judgment condition, and predicts the overdue rate of the rejected user after passing; the server determines a second determination condition according to the overdue rate and the passing rate; and the server performs wind control judgment on the user information of the rejected user, responds to the request of the terminal equipment and sends a judgment result to the terminal equipment. The invention improves the access rate of the user without increasing the overdue rate of the user, realizes the intellectualization of the wind control data processing, and meets the requirement of the real-time performance of the system.
Description
Technical Field
The present disclosure relates to the field of wind control data information processing technologies, and in particular, to a method, a system, and an electronic device for processing wind control data based on user information.
Background
With the development of computer technology, more and more technologies are applied to the field of risk control, and the field of wind control also puts higher requirements on safety and real-time performance. The risk identification capability is an important factor for health and rapid development of the relational enterprise, risk indexes are controlled in real time, risk situations of the risk indexes are pre-judged, potential risks are taken in advance, and the method is a main method for preventing systematic risks of the enterprise.
The prior art can not process the user wind control data intelligently and in real time through a computer or an information system, so that the risk index of a user can not be reduced while the access rate is not provided, and the requirements of system intelligence and real time are met.
Disclosure of Invention
In order to solve the above problems, an object of the present disclosure is to provide a method, a system and an electronic device for processing user information-based wind control data, which are used for processing user wind control data intelligently and in real time through a computer or an information system, so as to improve the user's access rate without increasing the user's overdue rate, thereby reducing the user's risk index while ensuring the number of users.
In a first aspect, an embodiment of the present disclosure provides a method for processing wind control data based on user information, including: the server acquires user information of a plurality of rejected users after wind control audit; the server determines a first judgment condition influencing the refusal of the refused user, and adjusts the first judgment condition according to a preset step length; the judgment conditions comprise a plurality of judgment indexes with different dimensions; the server determines the passing rate of the rejected user after passing according to the user information and the adjusted first judgment condition, and predicts the overdue rate of the rejected user after passing according to a preset credit scoring model; the server determines a second determination condition according to the overdue rate and the passing rate; and the server performs wind control judgment on the user information of the rejected user according to the second judgment condition, responds to the request of the terminal equipment and sends a judgment result to the terminal equipment.
In a possible implementation manner, in the method for processing wind control data based on user information provided by an embodiment of the present disclosure, the adjusting the first determination condition according to a preset step includes: and adjusting one or more judgment indexes of multiple different dimensions in the first judgment condition according to a preset step length, wherein the multiple rejected users are users who are rejected after wind control auditing according to the first judgment condition.
In a possible implementation manner, in the method for processing wind control data based on user information according to an embodiment of the present disclosure, the determining, according to the user information and the adjusted first determination condition, a passing rate of the rejected user after passing includes: according to the user information and thresholds corresponding to the adjusted judgment indexes with different dimensionalities, carrying out wind control verification on the rejected user again, and determining the number of the rejected users after the rejected users pass; and calculating the passing rate of the rejected users according to the number of the passed users.
In a possible implementation manner, in the method for processing wind control data based on user information according to an embodiment of the present disclosure, the predicting an overdue rate after a rejected user passes through according to a preset credit scoring model includes: predicting default probability of each rejected user after the rejected user passes through according to a preset credit scoring model; determining whether the rejected user is overdue or not after passing according to the default probability and a preset overdue critical value; and calculating the overdue rate of each rejected user after the passage according to the information about whether the each rejected user is overdue after the passage.
In a possible implementation manner, in the method for processing wind control data based on user information according to an embodiment of the present disclosure, the predicting a default probability after each rejected user passes through according to a preset credit scoring model includes: according to the user information of the rejected user, determining sales information of the rejected user within a preset time period, wherein the sales information comprises sales index data of a plurality of different dimensions; determining a weight coefficient corresponding to each dimension of sales index data; and determining the default probability after the rejected user passes according to the weight coefficient corresponding to the sales index data of each dimension and the sales index data of each dimension.
In a possible implementation manner, in the method for processing wind control data based on user information provided by an embodiment of the present disclosure, the preset overdue critical value is determined as follows: presetting a overdue initial critical value, adjusting the overdue initial critical value according to a preset step length, and determining the values of a first index and a second index according to the critical value after each adjustment; and determining a difference value between the first index and the second index according to the values of the first index and the second index, and taking a critical value corresponding to the maximum difference value as the overdue critical value.
In a possible implementation manner, in the method for processing wind control data based on user information according to an embodiment of the present disclosure, the determining a second determination condition according to the overdue rate and the pass rate includes: and according to the overdue rate and the passing rate, when the difference between the passing rate and the overdue rate is determined to be the maximum, determining the threshold values corresponding to the judgment indexes of the plurality of different dimensions corresponding to the group as the second judgment condition.
In a possible implementation manner, in the above method for processing wind control data based on user information provided by an embodiment of the present disclosure, the multiple different-dimensional determination indicators at least include: the outstanding loan balance, the number of overdue loan strokes in the preset time, the number of times of legal change in the preset time, the number of times of case-related invoices in the preset time, the proportion of the real payment fund, the equity quality-giving amount and the total amount of invoices in the preset time.
In a second aspect, an embodiment of the present disclosure provides a user information-based wind control data processing system, which includes: the acquiring unit is used for acquiring user information of a plurality of rejected users after wind control auditing; the adjusting unit is used for determining a first judging condition influencing the refusing of the refused user and adjusting the first judging condition according to a preset step length; the judgment conditions comprise a plurality of judgment indexes with different dimensions; the prediction unit is used for determining the passing rate of the rejected user after passing according to the user information and the adjusted first judgment condition, and predicting the overdue rate of the rejected user after passing according to a preset credit scoring model; a determining unit, configured to determine a second determination condition according to the overdue rate and the passage rate; and the output unit is used for auditing the user information of the rejected user according to the second judgment condition, responding to the request of the terminal equipment and sending an auditing result to the terminal equipment.
In a third aspect, the present disclosure provides a computer-readable medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for processing wind control data based on user information according to any one of the foregoing methods provided in the embodiments of the present disclosure.
In a fourth aspect, an embodiment of the present disclosure provides an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods for processing wind control data based on user information according to the embodiments of the present disclosure by executing the executable instructions.
The beneficial effects of this disclosure are as follows:
the invention improves the access rate of the user without increasing the overdue rate of the user, realizes the intellectualization of the wind control data processing, and meets the requirement of the real-time performance of the system.
Drawings
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 disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:
fig. 1 schematically illustrates a flowchart of a method for processing wind-controlled data based on user information in an exemplary embodiment of the present disclosure;
FIG. 2 schematically illustrates a flow chart of a method of passing rate calculation in an exemplary embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow chart of a method of calculating the overdue rate after passage of a rejected user in an exemplary embodiment of the disclosure;
FIG. 4 is a flow chart schematically illustrating a method for calculating a default probability after a rejected user passes through an exemplary embodiment of the present disclosure;
FIG. 5 is a block diagram illustrating a system for controlling data processing based on user information according to an exemplary embodiment of the present disclosure;
fig. 6 schematically shows a schematic structural diagram of a computer system of an electronic device suitable for implementing an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The embodiment of the disclosure provides a wind control data processing method based on user information, a device thereof, a computer readable medium and an electronic device, which are exemplarily used in the field of financial wind control, but not limited to the field.
Referring to fig. 1, a method for processing wind control data based on user information according to an embodiment of the present disclosure includes:
and S101, the server acquires user information of a plurality of rejected users after wind control verification.
Specifically, the rejected user in the present disclosure refers to a client who has a risk and is rejected to loan after the client passes the review of the initial loan risk rule, where the initial loan risk rule refers to a wind control rule before the rule is not adjusted according to the adjustment method provided in the present application. Rejected users generally refer to enterprises. The user information may include basic information of the user, behavior data, and financial data, wherein the basic information may include, but is not limited to, a name of the enterprise, a tax payment identification code, a size of the enterprise, and the like, data for characterizing the nature of the enterprise and identifying the enterprise; the behavior data can include but is not limited to the information used for representing the data of the behavior of the user, such as the times of change of enterprise legal persons, the times of complaints of judicial complaints and the like; the financial data may include, but is not limited to, real pay fund share, loan overdue amount, etc. information used to characterize the user's financial data.
For example, the financial data includes: the outstanding loan balance amount in the enterprise credit investigation, the overdue loan stroke amount in the last 2 years in the enterprise credit investigation, the percentage of the actual payment fund of the enterprise, the current equity quality fund amount of the enterprise and the total invoice making amount of the enterprise in the last one year. The behavioral data may include: the change times of the legal persons of the enterprise in the last year and the total number of the complaints of the judicial complaints of the enterprise in the last year.
It should be noted that, after the wind control audit, a batch of rejected users that do not pass the wind control audit are generally screened out, and in the present disclosure, the wind control determination condition is adjusted by using the user information and the number of the rejected users, so that the access rate of the rejected users is improved. Rejected users in this disclosure generally refer to enterprises.
Step S102, the server determines a first judgment condition influencing the refusal of the refused user, and adjusts the first judgment condition according to a preset step length, wherein the judgment condition comprises a plurality of judgment indexes with different dimensions.
Specifically, when the user passes the wind control audit, the user can be audited from the information of multiple dimensions. Generally, there may be 230 decision metrics for multiple different dimensions, but not all dimensions of data may directly affect the user rejection. In the disclosure, through the user information of the rejected user or through historical wind control audit data, data of multiple dimensions directly influencing rejection of the user are determined, and judgment indexes of the multiple dimensions are used as judgment conditions in the disclosure. The decision conditions may include decision metrics for a plurality of different dimensions, for example, may include correlation data for 7 audit dimensions.
Optionally, in the present disclosure, the multiple different-dimensional determination indicators may include: the outstanding loan balance, the number of overdue loan strokes in the preset time, the number of times of legal change in the preset time, the number of times of case-related invoices in the preset time, the proportion of the real payment fund, the equity quality-giving amount and the total amount of invoices in the preset time. The preset time period may be adjusted according to the actual condition, for example, the preset time period may be 1 year, 2 years, or half a year, and is not limited specifically herein.
For example, the determination condition may include 7 determination indicators with different dimensions, for example, the 7 determination indicators may be: the balance number of outstanding loans in the credit investigation of the enterprise, the overdue number of loans in the last 2 years in the credit investigation of the enterprise, the percentage number of the capital fund actually paid by the enterprise, the current share right quality fund number of the enterprise, the total amount of invoicing money of the enterprise in the last year, the change number of the legal persons of the enterprise in the last year and the total amount of the complaints and complaints of the enterprise in the last year.
Note that, the number of overdue loans in the last 2 years in the enterprise credit investigation may be the number of overdue loans in the last 3 years or the last 1 year in the enterprise credit investigation, and the time in the determination index is not particularly limited in this disclosure. For example, the total amount of invoicing of the enterprise in the last year may be the total amount of invoicing of the enterprise in the last two years, and is not particularly limited herein. In addition, the first determination condition and the second determination condition mentioned later in the present disclosure are merely to distinguish the corresponding determination conditions before and after the adjustment rule. The first judgment condition is a plurality of dimensionality judgment indexes determined before the threshold is not adjusted after the wind control auditing is passed. The second determination condition is a determination index of a plurality of dimensions determined after adjustment by a threshold value. Therefore, the first determination condition and the second determination condition differ only in the determination index threshold value.
And S103, the server determines the passing rate of the rejected user after passing according to the user information and the adjusted first judgment condition, and predicts the overdue rate of the rejected user after passing according to a preset credit scoring model.
Specifically, after the first determination condition is adjusted according to the step length each time, a new set of determination conditions, that is, a new set of determination indexes, is formed, the wind-controlled review is performed on the user information again through the plurality of different-dimensional determination indexes in the set of data, and the passing rate of the rejected user corresponding to the set of data after the re-review is calculated. The preset credit scoring model can predict the overdue rate of the rejected user, and after the wind control audit is conducted again, the original rejected user can pass the wind control audit, and the overdue rate of the user can be predicted through the credit scoring model.
The overdue rate after the passed of the rejected user is obtained by predicting according to the user data of the rejected user and a preset credit scoring model. The preset credit scoring model is obtained by training historical data, and the training process and the prediction mode of the model will be described in detail later.
And step S104, the server determines a second determination condition according to the overdue rate and the passing rate.
Specifically, the first determination condition is adjusted according to the step length each time, and then the one-pass rate and the overdue rate are calculated, that is, how many times the first determination condition is adjusted, and how many times the values of the pass rate and the overdue rate are correspondingly obtained.
The second determination condition is the adjusted determination index threshold values of the plurality of different dimensions.
According to the method for processing the wind control data based on the user information, firstly, the user information of a plurality of rejected users after wind control verification is obtained; secondly, determining a first judgment condition influencing the refusal of the refused user, and adjusting the first judgment condition according to a preset step length, wherein the judgment condition comprises a plurality of judgment indexes with different dimensions; then determining the passing rate of the rejected user after passing according to the user information and the adjusted first judgment condition, and predicting the overdue rate of the rejected user after passing according to a preset credit scoring model; and finally, determining a second determination condition according to the overdue rate and the passing rate. Therefore, in the method for processing the wind control data based on the user information provided by the embodiment of the disclosure, the passing rate of the rejected user is improved by adjusting the judgment indexes of a plurality of different dimensions influencing the rejection of the rejected user, and the overdue rate is calculated for the rejected user, so that the overdue rate of the user is controlled while the passing rate of the user is improved, and the loan risk of the user is avoided to be increased.
In an exemplary embodiment, in the method for processing wind control data based on user information provided by the embodiment of the present disclosure, the adjusting the first determination condition according to a preset step size in step S102 includes: and adjusting one or more judgment indexes of multiple different dimensions in the first judgment condition according to a preset step length, wherein the multiple rejected users are users who are rejected after the first judgment condition is used for wind control examination.
Specifically, in adjusting the first determination condition in the present disclosure, only one or more of the determination indexes may be adjusted. For example, the determination conditions include determination indexes of 7 dimensions, which are the number of outstanding loan balance in the enterprise credit, the number of overdue loan strokes in the last 2 years in the enterprise credit, the percentage of the actual payment fund of the enterprise, the current number of the equity liquidation fund of the enterprise, the total number of invoicing fees of the enterprise in the last year, the number of change of the legal person of the enterprise in the last year, and the total number of the complaint notice of the enterprise in the last year. The judgment index data of 7 dimensions are respectively that the threshold corresponding to the number of outstanding loan balance in the enterprise credit is 300 ten thousand, the corresponding threshold corresponding to the number of overdue strokes of loan in the last 2 years in the enterprise credit is 6, the threshold of the current number of capital outlay of the enterprise is 1000 ten thousand, the threshold of the percentage of the actual payment capital fund of the enterprise is 50%, the threshold of the total number of invoicing funds of the enterprise in the last year is 150 ten thousand, the threshold of the number of legal change times of the enterprise in the last year is 5, and the threshold of the total number of official complaints concerning the enterprise in the last year is 10.
When the first determination condition is adjusted, the determination index of only one dimension may be adjusted according to the step length, for example, the threshold corresponding to the number of outstanding loan balance in the enterprise credit is adjusted to 350 ten thousand, and the wind-controlled review is performed again on the rejected user by using the 350 ten thousand threshold and the determination index thresholds of other 6 dimensions. Or, adjusting the 7-dimensional determination indexes according to the step length, for example, adjusting the threshold corresponding to the number of outstanding loan balance in the credit investigation of the enterprise to 350 ten thousand, adjusting the corresponding threshold to the number of overdue loan strokes in the last 2 years in the credit investigation of the enterprise to 7, adjusting the threshold of the current number of capital right discharge money of the enterprise to 1500 ten thousand, adjusting the threshold of the percentage of actual capital money paid by the enterprise to 60%, adjusting the threshold of the total amount of invoicing money in the last year by the enterprise to 100 ten thousand, adjusting the threshold of the number of change of legal persons in the last year by the enterprise to 6, and adjusting the threshold of the total amount of legal complaints and complaints in the last year by the enterprise to 11, so that the adjusted 7-dimensional determination index threshold is used as a wind-controlled auditing standard for the rejected user again. Similarly, only the determination indexes of 2 or 3 or 4 or even more different dimensions in the 7 dimensions may be adjusted. And is not particularly limited herein.
It should be noted that after the determination index is adjusted each time, a plurality of permutation combinations with different threshold values are generated, each permutation combination corresponds to a new first determination condition, and the wind-controlled audit is performed on the rejected user according to the new first determination condition. The self-defined step length can be carried out according to the type of the judgment index by adjusting the threshold value according to the preset step length. For example, if the corresponding threshold value of the overdue number of loans in the last 2 years in the enterprise credit investigation is 6, the adjustment can be performed according to the step length of 1, and the corresponding threshold values of the overdue number of loans in the last 2 years in the enterprise credit investigation are sequentially increased; for another example, if the percentage of the actual payment fund of the enterprise is 50%, the threshold may be adjusted according to the step length of 1% or 2% or 10%; or, if the threshold corresponding to the number of outstanding loan balance in the credit investigation of the enterprise is 300 ten thousand, the threshold may be adjusted so that the step length is 1 ten thousand, or 5 ten thousand, or 10 ten thousand. Therefore, the present disclosure is not limited to the length and the number of the step length.
It should be emphasized that, when adjusting the threshold, the adjustment needs to be made in consideration of the actual situation. For example, the threshold corresponding to the amount of outstanding loan balance in the enterprise credit investigation is 300 ten thousand, and when the threshold is increased, the amount cannot be increased infinitely, otherwise the order is rejected, and the adjustment is needed according to the actual situation. Similarly, the threshold adjustment modes of other dimensions also need to be adjusted according to actual conditions, and cannot be infinite or infinite.
And step S105, the server performs wind control judgment on the user information of the rejected user according to the second judgment condition, responds to the request of the terminal equipment, and sends a judgment result to the terminal equipment.
In an exemplary embodiment, in the method for processing wind control data based on user information provided in the embodiment of the present disclosure, referring to fig. 2, the determining, in step S103, a passing rate of the rejected user according to the user information and the adjusted determination condition includes:
step S201, according to the user information and the threshold values corresponding to the adjusted judgment indexes with different dimensionalities, carrying out wind control verification on the rejected users again, and determining the number of the rejected users after the rejected users pass;
and step S202, determining the passing rate of the rejected users according to the number of the passed users.
Specifically, performing wind control audit on the refused user according to the user information and the adjusted threshold values corresponding to the multiple different-dimension determination indexes comprises comparing the user information of the refused user with the threshold values of the multiple different-dimension determination indexes adjusted by each group of threshold values, and if the user information of the refused user is in the range of the adjusted threshold values of the multiple different-dimension determination indexes, determining that the wind control audit on the user can be released, and considering that the user does not have loan risk, namely that the refused user passes the audit. And adjusting and calculating the number of passing users after all the rejected users are checked again aiming at each group of threshold values, and taking the ratio of the number of passing users to all the rejected users as the passing rate in the embodiment of the disclosure.
In an exemplary embodiment, in the method for processing wind control data based on user information provided in the embodiment of the present disclosure, referring to fig. 3, in step S103, predicting an overdue rate after a rejected user passes through according to a preset credit scoring model, including:
step S301, predicting default probability of each rejected user after the rejected user passes through according to a preset credit scoring model;
step S302, determining whether the user is overdue after being refused to pass according to the default probability and a preset overdue critical value;
and step S303, determining the overdue rate of the rejected user after the rejected user passes according to the information whether the rejected user passes the overdue rate or not.
The preset credit scoring model is obtained by training the historical full-scale data through a logistic regression machine learning algorithm. Specifically, the first step is to acquire historical full data, wherein the full data comprises user data with overdue repayment and user data with non-overdue repayment, the user with overdue repayment is used as a bad sample, and the user with normal repayment is used as a good sample. Step two, obtaining sales data of each user, for example, the sales data may include: using standard deviation of transaction amount, inclination of time series curve of monthly transaction amount, days from the earliest invoicing time to the present, proportion of red amount of the invoice in the last 12 months, proportion of transaction amount of enterprises at the downstream of TOP10 in the last 12 months, proportion of the transaction amount in the last 6 months, proportion of the transaction amount in the last 3 months, the number of invoices in the last 3 months and the average invoicing amount in the last 12 months. And step three, performing model training through a logistic regression machine learning algorithm, so that the input of the model is sales data output which is default probability.
It should be noted that the above training of the credit scoring model may use other machine learning algorithms, and is not limited in this respect. In addition, the sales data in the input of the model is only one form to be provided, and other sales data, behavior data, or the like may be used.
Specifically, the default probability is a decimal between 0 and 1, a larger numerical value indicates that the probability of default is higher, and in order to clearly determine that the user is overdue when the default rate of the user exceeds a certain threshold, the embodiment of the present disclosure provides a manner of determining an overdue critical value, optionally, a overdue initial critical value is preset, the overdue initial critical value is adjusted according to a preset step length, and a value according to the first index and the second index is determined according to the critical value adjusted each time; and determining a difference value between the first index and the second index according to the values of the first index and the second index, and taking a critical value corresponding to the maximum difference value as an overdue critical value.
The first index is used for representing the probability of the result of predicting the bad sample to be correct. Specifically, the default probability of the user is predicted according to the credit scoring model, the user sample is determined to be a bad sample when the default probability exceeds the overdue critical value, if the sample really belongs to the bad sample, the sample is considered to be predicted correctly, finally, the ratio of the number of the samples with correct prediction to all the samples is calculated, and the ratio is used as the value of the first index. For example, when the overdue threshold is 0.17, the user is considered to be overdue when the default rate predicted by the credit scoring model is greater than 0.17, otherwise, the user is considered not to be overdue.
The second index is used to indicate the probability that the predicted sample result is erroneous. Specifically, the default probability of the user is predicted according to the credit scoring model, the user sample is determined to be a bad sample when the default probability exceeds the overdue critical value, if the sample belongs to a good sample, the sample is considered to be a prediction error, finally, the ratio of the number of the prediction errors to all the samples is calculated, and the ratio is used as a second index value.
And finally, taking the overdue critical value corresponding to the maximum difference value of the first index and the second index as a standard for judging whether the user is overdue.
It should be noted that the overdue initial threshold in the present disclosure includes, but is not limited to, being set empirically. After the credit scoring model is trained, the overdue critical value is further trained through full data, and therefore the preset credit scoring model and the overdue critical value are obtained.
In an exemplary embodiment, in the method for processing wind control data based on user information provided in the embodiment of the present disclosure, referring to fig. 4, predicting the default probability after each rejected user passes through according to a preset credit scoring model, includes:
step S401, according to the user information of the rejected user, determining sales information of the rejected user within a preset time period, wherein the sales information comprises a plurality of sales index data with different dimensions;
step S402, determining a weight coefficient corresponding to each dimension of sales index data;
step S403, determining default probability after the rejected user passes through according to the weighting coefficient corresponding to each dimension sales index data and each dimension sales index data.
Specifically, the sales information of the rejected user comprises standard deviation of transaction amount, inclination of time series curve of monthly transaction amount, days from the earliest invoicing time to the latest, proportion of money flushed by invoices in the last 12 months, proportion of transaction amount of enterprises downstream of TOP10 in the last 12 months, proportion of transaction amount in the last 6 months, proportion of transaction amount in the last 3 months, number of invoices in the last 3 months and average invoices in the last 12 months. After the user data is acquired, the 9-dimensional sales index data is input into a credit scoring model to be used for predicting the default rate of the rejected user. When the default probability is calculated according to the credit scoring model, the weight coefficient of the corresponding gear is mainly determined by the sales index data range aiming at each dimension, so that the default probability is calculated according to the weight coefficient. The sales index data of the 9 dimensions correspond to different value range intervals according to the value range, and correspond to different weight coefficients according to the value range intervals.
For example, if the proportion of the amount of the invoice flushed in the last 12 months is less than or equal to 0, the invoice corresponds to a first value range, the weight coefficient corresponding to the first value range is-0.36, and if the proportion of the amount of the invoice flushed in the last 12 months is greater than 0, the corresponding weight coefficient is 0.37; if the number of days from the earliest invoicing time to the latest is less than or equal to 700, the corresponding weight coefficient is 0.30, and if the number of days from the earliest invoicing time to the latest is greater than 1100, the corresponding weight coefficient is-1.13; if the weight coefficient is larger than 700 and less than or equal to 900, the corresponding weight coefficient is 0.98, and if the weight coefficient is larger than 900 and less than or equal to 1100, the corresponding weight coefficient is-0.15. Table 1 below shows specific parameters of a credit scoring model provided by the present disclosure.
TABLE 1
Optionally, the default probability calculation method provided by the present disclosure is:
K＝1/(1+exp(-(x1+x2+x3+x4+x5+x6+x7+x8+x9)))
wherein, K is default probability, x1, x2, x3, x4, x5, x6, x7, x8 and x9 are weight coefficients corresponding to 9 dimension sales indicators respectively, and exp is an exponential function.
It should be noted that the above is only the credit scoring model determined according to the 9-dimensional sales index, but the model is not limited to the input dimension of 9, and the number of the input dimensions may be increased or decreased.
In an exemplary embodiment, in the method for processing wind control data based on user information provided by the embodiment of the present disclosure, determining the first determination condition according to the overdue rate and the passing rate includes: and according to the overdue rate and the passing rate, when the difference between the passing rate and the overdue rate is determined to be the maximum, determining the threshold values corresponding to the judgment indexes of the plurality of different dimensions corresponding to the group as second judgment conditions.
Specifically, after a group of new determination conditions is formed by adjusting the threshold value each time, the rejected user is re-audited, and when it is determined that the rejected user meets the adjusted first determination condition, the rejected user is determined to pass the audit, and further whether the user is overdue is predicted through a credit scoring model. After the threshold values corresponding to all the judgment indexes are adjusted, a plurality of groups of passing rates and overdue rates are formed. And then calculating the difference between the passing rate and the overdue money in each group, and taking the judgment index threshold corresponding to the maximum difference as a second judgment condition.
Alternatively, after the passage rate and the overdue rate are determined each time the threshold is adjusted, the lifting ratio of the corresponding passage rate to the passage rate of the first determination condition is determined, the lifting ratio of the overdue rate is calculated, and the set of determination conditions in which the lifting ratio of the passage rate is the largest and the lifting ratio of the overdue rate is the smallest is used as the second determination condition.
The passing rate is a ratio of the number of the users to be rejected after passing the passage to the number of the users to be rejected. The overdue rate is the ratio of the number of overdue users passing the rejected user to the number of overdue users passing the rejected user.
The calculation method of the throughput rate increase ratio is as follows: the method comprises the steps of firstly calculating the proportion of the number of a plurality of rejected users to all wind control audits after the wind control audits, taking the proportion as a first passing rate, then calculating the proportion of the number of rejected users to all wind control audits after the audits are carried out by utilizing the adjusted first judging conditions, taking the proportion as a second passing rate, and finally calculating the difference value or the ratio of the second passing rate to the first passing rate.
Similarly, the overdue lift ratio is calculated as follows: firstly, determining users who pass the audit after the wind control audit, predicting the default rate of the users who pass the audit, taking the number of the users exceeding the default probability as the number of overdue users, finally calculating the proportion of the number of the overdue users in all the wind control audits, and taking the proportion as a first overdue rate; then calculating the overdue rate corresponding to the adjusted first judgment condition as a second overdue rate according to the mode; and finally, calculating the difference or ratio of the first overdue rate and the second overdue rate.
In summary, the determination condition adjustment method provided by the present disclosure mainly adjusts a plurality of determination indexes with different dimensions that affect the refusal of the refused user, and then determines the corresponding passage rate and expiration rate based on each adjustment, and uses the determination index corresponding to the case where the passage rate is increased the highest and the expiration rate is increased the lowest as a second determination condition for performing a wind-controlled audit on an enterprise, so as to increase the passage rate of the refused user, and calculate the expiration rate for the passing refused user, so that the user passage rate is increased while the user expiration rate is controlled, and the loan risk of the user is prevented from being increased.
It is noted that the above-mentioned figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Based on the same inventive concept, referring to fig. 5, an embodiment of the present disclosure provides a wind-control data processing system based on user information, including:
the acquiring unit 61 is used for acquiring user information of a plurality of rejected users after wind control auditing;
an adjusting unit 62, configured to determine a first determination condition that affects the refusal of the refused user, and adjust the first determination condition according to a preset step length; the judgment conditions comprise a plurality of judgment indexes with different dimensions;
a prediction unit 63, configured to determine, according to the user information and the adjusted first determination condition, a passing rate of the rejected user after passing through the prediction unit, and predict, according to a preset credit scoring model, an overdue rate of the rejected user after passing through the prediction unit;
a determining unit 64, configured to determine a second determination condition according to the overdue rate and the passing rate;
and the output unit 65 is configured to audit the user information of the rejected user according to the second determination condition, respond to a request of the terminal device, and send an audit result to the terminal device.
In a possible implementation manner, in the above-mentioned wind control data processing system based on user information provided in this embodiment of the present disclosure, the adjusting unit 62 adjusts the first determination condition according to a preset step size, specifically to: and adjusting one or more judgment indexes of multiple different dimensions in the first judgment condition according to a preset step length, wherein the multiple rejected users are users who are rejected after wind control auditing according to the first judgment condition.
In a possible implementation manner, in the above-mentioned wind control data processing system based on user information provided by this embodiment of the present disclosure, the adjusting unit 62 determines, according to the user information and the adjusted first determination condition, a passing rate after the passage of the rejected user, and specifically is configured to: according to the user information and thresholds corresponding to the adjusted judgment indexes with different dimensionalities, carrying out wind control verification on the rejected user again, and determining the number of the rejected users to pass; and determining the passing rate of the rejected users according to the number of the passed users.
In a possible implementation manner, in the wind-control data processing system based on user information provided in the embodiment of the present disclosure, the predicting unit 63 predicts an overdue rate after the user is rejected according to a preset credit scoring model, and is specifically configured to: predicting default probability of each rejected user after the rejected user passes through according to a preset credit scoring model; determining whether the rejected user is overdue or not after passing according to the default probability and a preset overdue critical value; and determining the overdue rate of each rejected user after the passage according to the information whether the each rejected user is overdue after the passage.
In a possible implementation manner, in the wind control data processing system based on user information provided by the embodiment of the present disclosure, the predicting unit 63 predicts the default probability after each rejected user passes through according to a preset credit scoring model, and includes: according to the user information of the rejected user, determining sales information of the rejected user within a preset time period, wherein the sales information comprises sales index data of a plurality of different dimensions; determining a weight coefficient corresponding to each dimension of sales index data; and determining the default probability after the rejected user passes according to the weight coefficient corresponding to the sales index data of each dimension and the sales index data of each dimension.
In a possible implementation manner, in the above-mentioned wind-control data processing system based on user information provided by an embodiment of the present disclosure, the preset overdue threshold value is determined by: presetting a overdue initial critical value, adjusting the overdue initial critical value according to a preset step length, and determining the values of a first index and a second index according to the critical value after each adjustment; and determining a difference value between the first index and the second index according to the values of the first index and the second index, and taking a critical value corresponding to the maximum difference value as the overdue critical value.
In a possible implementation manner, in the above-mentioned wind control data processing system based on user information provided by an embodiment of the present disclosure, the determining unit 64 determines the second determination condition according to the overdue rate and the pass rate, and includes: and according to the overdue rate and the passing rate, when the difference between the passing rate and the overdue rate is determined to be the maximum, determining the threshold values corresponding to the judgment indexes of the plurality of different dimensions corresponding to the group as the second judgment condition.
In a possible implementation manner, in the above-mentioned wind control data processing system based on user information provided by an embodiment of the present disclosure, the multiple determination indicators with different dimensions include: the outstanding loan balance, the number of overdue loan strokes in the preset time, the number of times of legal change in the preset time, the number of times of case-related invoices in the preset time, the proportion of the real payment fund, the equity quality-giving amount and the total amount of invoices in the preset time.
The specific details of each module in the above apparatus have been described in detail in the method section, and details that are not disclosed may refer to the method section, and thus are not described again.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Based on the same inventive concept, the disclosed embodiments provide a computer-readable medium, on which a computer program is stored, which when executed by a processor implements any of the above-mentioned wind control data processing methods based on user information as provided by the disclosed embodiments.
It should be noted that the computer system 700 of the electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments of the present disclosure.
As shown in fig. 6, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for system operation are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.
In particular, the processes described below with reference to the flowcharts may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program, when executed by a Central Processing Unit (CPU)701, performs various functions defined in the methods and apparatus of the present application. In some embodiments, computer system 700 may also include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.
It should be noted that the computer readable media shown in the present disclosure may be computer readable signal media or computer readable storage media or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
Based on the same inventive concept, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement any of the above-described methods for processing the wind control data based on the user information.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements 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 (10)
1. A wind control data processing method based on user information is characterized by comprising the following steps:
user information data of a plurality of rejected users after wind control verification are obtained through a server;
determining a first judgment condition influencing the refusal of the refused user through a server, and adjusting the first judgment condition according to a preset step length, wherein the first judgment condition comprises a plurality of judgment indexes with different dimensions;
the server determines the passing rate of the rejected user after passing according to the user information data and the adjusted first judgment condition, and predicts the overdue rate of the rejected user after passing according to a preset credit scoring model;
the server determines a second determination condition according to the overdue rate and the passing rate;
and the server performs wind control judgment on the user information of the rejected user according to the second judgment condition, responds to the request of the terminal equipment and sends a judgment result to the terminal equipment.
2. The method of claim 1, wherein the adjusting the first decision condition according to the preset step size comprises:
and adjusting the judgment index of one or more dimensions of a plurality of different dimensions in the first judgment condition according to a preset step length, wherein the rejected users are users rejected after wind control audit is carried out on the rejected users through the first judgment condition.
3. The method according to claim 1, wherein the determining the passing rate after the user passage refusal according to the user information and the adjusted first determination condition comprises:
carrying out wind control judgment on the rejected user again according to the user information and the threshold values corresponding to the adjusted judgment indexes with different dimensionalities, and determining the number of the rejected users after the rejected users pass;
and determining the passing rate of the rejected users according to the number of the passed users.
4. The method of claim 1, wherein predicting the overdue rate after the rejected user passes according to a preset credit scoring model comprises:
predicting default probability of each rejected user after the rejected user passes through according to a preset credit scoring model;
determining whether the rejected user is overdue or not after passing according to the default probability and a preset overdue critical value;
and determining the overdue rate of each rejected user after the passage according to the information whether the each rejected user is overdue after the passage.
5. The method of claim 4, wherein predicting the default probability of each rejected user after passing through the system according to a preset credit scoring model comprises:
according to the user information of the rejected user, determining sales information of the rejected user within a preset time period, wherein the sales information comprises sales index data of a plurality of different dimensions;
determining a weight coefficient corresponding to each dimension of sales index data;
and determining the default probability after the rejected user passes according to the weight coefficient corresponding to the sales index data of each dimension and the sales index data of each dimension.
6. The method of claim 4, wherein the pre-set timeout threshold is determined by:
presetting a overdue initial critical value, adjusting the overdue initial critical value according to a preset step length, and determining the values of a first index and a second index according to the critical value after each adjustment;
and determining a difference value between the first index and the second index according to the values of the first index and the second index, and taking a critical value corresponding to the maximum difference value as an overdue critical value.
7. The method of claim 1, wherein determining a second determination condition based on the overdue rate and the pass rate comprises:
and according to the overdue rate and the passing rate, when the difference between the passing rate and the overdue rate is determined to be the maximum, determining the threshold values corresponding to the judgment indexes of the plurality of different dimensions corresponding to the group as the second judgment condition.
8. The method of claim 1, wherein the plurality of decision metrics for different dimensions comprises at least: the outstanding loan balance, the number of overdue loan strokes in the preset time, the number of times of legal change in the preset time, the number of times of case-related invoices in the preset time, the proportion of the real payment fund, the equity quality-giving amount and the total amount of invoices in the preset time.
9. A system for processing wind-controlled data based on user information, comprising:
the acquiring unit is used for acquiring user information of a plurality of rejected users after wind control auditing;
the adjusting unit is used for determining a first judging condition influencing the refusing of the refused user and adjusting the first judging condition according to a preset step length; the judgment conditions comprise a plurality of judgment indexes with different dimensions;
the prediction unit is used for determining the passing rate of the rejected user after the rejected user passes according to the user information and the adjusted first judgment condition, and predicting the overdue rate of the rejected user after the rejected user passes according to a preset credit scoring model;
a determining unit, configured to determine a second determination condition according to the overdue rate and the passage rate;
and the output unit is used for auditing the user information of the rejected user according to the second judgment condition, responding to the request of the terminal equipment and sending an auditing result to the terminal equipment.
10. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the method for processing wind control data based on user information according to any one of claims 1 to 8 via executing the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111211828.8A CN113962796A (en) | 2021-10-18 | 2021-10-18 | Wind control data processing method and system based on user information and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111211828.8A CN113962796A (en) | 2021-10-18 | 2021-10-18 | Wind control data processing method and system based on user information and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113962796A true CN113962796A (en) | 2022-01-21 |
Family
ID=79464308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111211828.8A Pending CN113962796A (en) | 2021-10-18 | 2021-10-18 | Wind control data processing method and system based on user information and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113962796A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146671A (en) * | 2018-08-28 | 2019-01-04 | 卫盈联信息技术（深圳）有限公司 | Air control method, apparatus and computer readable storage medium |
| CN109389486A (en) * | 2018-08-27 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Loan air control rule adjustment method, apparatus, equipment and computer storage medium |
| CN110659985A (en) * | 2019-09-30 | 2020-01-07 | 上海淇玥信息技术有限公司 | Method and device for fishing back false rejection potential user and electronic equipment |
| CN111461857A (en) * | 2020-03-03 | 2020-07-28 | 福建省农村信用社联合社 | Personal online credit method, device, system, equipment and medium for small and medium-sized banks |
| CN111915109A (en) * | 2019-05-07 | 2020-11-10 | 北京水滴互保科技有限公司 | Medical financing device, system and method |
| CN112528887A (en) * | 2020-12-16 | 2021-03-19 | 支付宝(杭州)信息技术有限公司 | Auditing method and device |
| CN112529481A (en) * | 2021-02-08 | 2021-03-19 | 北京淇瑀信息科技有限公司 | User fishing-back method and device and electronic equipment |
| WO2021057130A1 (en) * | 2019-09-26 | 2021-04-01 | 支付宝(杭州)信息技术有限公司 | Intelligent risk control decision-making method and system, service processing method and system |
-
2021
- 2021-10-18 CN CN202111211828.8A patent/CN113962796A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389486A (en) * | 2018-08-27 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Loan air control rule adjustment method, apparatus, equipment and computer storage medium |
| CN109146671A (en) * | 2018-08-28 | 2019-01-04 | 卫盈联信息技术（深圳）有限公司 | Air control method, apparatus and computer readable storage medium |
| CN111915109A (en) * | 2019-05-07 | 2020-11-10 | 北京水滴互保科技有限公司 | Medical financing device, system and method |
| WO2021057130A1 (en) * | 2019-09-26 | 2021-04-01 | 支付宝(杭州)信息技术有限公司 | Intelligent risk control decision-making method and system, service processing method and system |
| CN110659985A (en) * | 2019-09-30 | 2020-01-07 | 上海淇玥信息技术有限公司 | Method and device for fishing back false rejection potential user and electronic equipment |
| CN111461857A (en) * | 2020-03-03 | 2020-07-28 | 福建省农村信用社联合社 | Personal online credit method, device, system, equipment and medium for small and medium-sized banks |
| CN112528887A (en) * | 2020-12-16 | 2021-03-19 | 支付宝(杭州)信息技术有限公司 | Auditing method and device |
| CN112529481A (en) * | 2021-02-08 | 2021-03-19 | 北京淇瑀信息科技有限公司 | User fishing-back method and device and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| FAL金科应用研究院: "《拒绝客户捞回方法》", 《HTTPS://ZHUANLAN.ZHIHU.COM/P/372293861》 * |
| 求是汪在路上: "《模型视角下的风控策略规则发现》", 《HTTPS://ZHUANLAN.ZHIHU.COM/P/141287611》 * |
| 陈文达: "经济新常态下担保公司风控理论的创新与实践", 《中国农业会计》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11461841B2 (en) | Statistical risk management system for lending decisions | |
| US20190114704A1 (en) | Statistical model for making lending decisions | |
| US20080120133A1 (en) | Method for predicting the payment of medical debt | |
| CN111192131A (en) | Financial risk prediction method and device and electronic equipment | |
| US11205222B2 (en) | Centralized model for lending risk management system | |
| WO2021032056A1 (en) | Method and apparatus for processing batch tasks, computing device and storage medium | |
| JP6559744B2 (en) | Information processing apparatus, information processing method, and program | |
| CA3081569A1 (en) | Entity segmentation for analysis of sensitivities to potential disruptions | |
| WO2016084642A1 (en) | Credit examination server, credit examination system, and credit examination program | |
| CN112017042A (en) | Resource quota determining method and device based on tweed distribution and electronic equipment | |
| CN110751549A (en) | Management and control method and device for overdue financial loan collection and acceptance promotion and electronic equipment | |
| CN110941644B (en) | Policy data generation method, device, equipment and storage medium | |
| CN111506876B (en) | Data predictive analysis method, system, equipment and readable storage medium | |
| CN112561685B (en) | Customer classification method and device | |
| CN113962796A (en) | Wind control data processing method and system based on user information and electronic equipment | |
| CN111144627A (en) | User overdue payment prediction method and device and electronic equipment | |
| CN114723481A (en) | Data processing method and device, electronic equipment and storage medium | |
| CA3087631C (en) | Centralized model for lending risk management system | |
| CN113450208A (en) | Loan risk change early warning and model training method and device | |
| Laia et al. | Decision Support System to Determine Applicant Housing Credits With SAW Method on the House Complex of J. City Residence by Capital Property | |
| CN112907362A (en) | Loan transaction processing method and device, electronic equipment and storage medium | |
| CN112907361A (en) | Method and device for processing loan application | |
| CN112102094A (en) | Method and apparatus for securitization and stratification of assets | |
| US20220093240A1 (en) | Apparatuses, systems, and methods for determining healthcare vitality | |
| US20230394069A1 (en) | Method and apparatus for measuring material risk in a data set |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |