CN112598225A - Evaluation index determination method and apparatus, storage medium, and electronic apparatus - Google Patents
Evaluation index determination method and apparatus, storage medium, and electronic apparatus Download PDFInfo
- Publication number
- CN112598225A CN112598225A CN202011403691.1A CN202011403691A CN112598225A CN 112598225 A CN112598225 A CN 112598225A CN 202011403691 A CN202011403691 A CN 202011403691A CN 112598225 A CN112598225 A CN 112598225A
- Authority
- CN
- China
- Prior art keywords
- target
- data structure
- evaluation
- analysis module
- strategy
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Abstract
The invention provides a method and a device for determining an evaluation index, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring a target data structure corresponding to a target object in a policy analysis module, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, and the policy is used for indicating whether resources are provided for the target object; inputting a target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained by using multiple groups of data through machine learning, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure; and judging whether the target evaluation index in the target evaluation report reaches an expected index or not so as to determine whether the decision meets a preset condition or not.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to a method and an apparatus for determining an evaluation index, a storage medium, and an electronic apparatus.
Background
In recent years, an intelligent wind control system constructed on the basis of artificial intelligence and big data technology develops rapidly, under the premise of effectively reducing the occurrence probability and loss of risk events, the intelligent wind control system expands service coverage crowds, perfects the service flow, reduces the wind control cost, realizes full chain automation before, during and after the user is credited in the consumption amount scene, and can promote the differentiation of wind control management. The intelligent wind control system is established, so that the limitation of traditional wind control of experience control in a manual mode is broken through, the core capability of the intelligent wind control system is to help financial institutions gradually change from regular flow driving to data driving and intelligent decision making, and the traditional complex wind control business flow is reshaped and modified. However, with the development of services, under the condition that the external environment, the supervision policy, the internal management and the fund can be changed continuously, the internet financial market changes in wind and cloud, the economic environment changes, the passenger group changes, the data source acquisition and other various internal and external factors can cause the deviation of the model score, and even errors occur.
Aiming at solving the problems that the accuracy of a policy analysis module is reduced and the like due to various internal and external factors such as economic environment, change of customer groups, data source acquisition and the like in the related technology, an effective technical scheme is not provided.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining an evaluation index, a storage medium and an electronic device, which are used for at least solving the problems that the accuracy of a policy analysis module is reduced and the like due to various internal and external factors such as economic environment, change of a customer group, data source acquisition and the like in the related art.
According to an embodiment of the present invention, there is provided an evaluation index determination method including: acquiring a target data structure corresponding to a target object in a policy analysis module, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object; inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained through machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure; and judging whether the target evaluation index in the target evaluation report reaches an expected index or not so as to determine whether the decision meets a preset condition or not.
Optionally, the obtaining of the target data structure corresponding to the target object in the policy analysis module includes: acquiring result information of a target object in the strategy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires a record of resources; and acquiring a target data structure corresponding to the target object from the result information.
Optionally, the policy monitoring model comprises: the method comprises the following steps of inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the evaluation indexes comprise: determining an evaluation strategy corresponding to the target data structure according to the input target data structure, and determining a target evaluation index corresponding to the evaluation strategy from a plurality of target evaluation indexes; analyzing the target data structure through a target evaluation index corresponding to the evaluation strategy; and determining a target evaluation report of the target data structure according to the analysis result.
Optionally, the evaluation index includes at least one of: the evaluation card characteristic quantity IV value, the contribution index value of the evaluation card as stability, the evaluation card K-S statistic value and the evaluation card Giyny coefficient value.
Optionally, the determining whether the target evaluation index in the target evaluation report reaches an expected index to determine whether the decision meets a preset condition includes: under the condition that a plurality of target evaluation indexes are contained in the target evaluation report, acquiring threshold value ranges of expected indexes corresponding to the target evaluation indexes; when the target evaluation indexes meet the threshold ranges of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report meets preset conditions, and making a decision generated by the strategy analysis module meet requirements; and under the condition that the target evaluation indexes do not meet the threshold range of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report does not meet the preset condition, and resetting the strategy analysis module if the decision generated by the strategy analysis module does not meet the requirement.
Optionally, after determining whether the target evaluation index in the target evaluation report reaches an expected index to determine whether the policy analysis module meets a preset condition, the method further includes: and under the condition that the strategy analysis module is confirmed to meet the preset conditions, executing the decision generated by the strategy analysis module, and storing the decision data information in a target evaluation report corresponding to the strategy analysis module.
According to an embodiment of the present invention, there is provided an evaluation index determination device including: an obtaining module, configured to obtain a target data structure corresponding to a target object in a policy analysis module, where the target data structure includes at least one of: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object; the evaluation module is configured to input the target data structure into a policy monitoring model to obtain a target evaluation report of the target data structure, where the policy monitoring model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: the target data structure and a target evaluation report corresponding to the target data structure; and the determining module is used for judging whether the target evaluation index in the target evaluation report reaches an expected index so as to determine whether the decision meets a preset condition.
Optionally, the obtaining module is further configured to: the acquisition module is further configured to: acquiring result information of a target object in the strategy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires a record of resources; and acquiring a target data structure corresponding to the target object from the result information.
Optionally, the evaluation module further includes: the evaluation indexes are further used for determining an evaluation strategy corresponding to the target data structure according to the input target data structure and determining a target evaluation index corresponding to the evaluation strategy from a plurality of target evaluation indexes; analyzing the target data structure through a target evaluation index corresponding to the evaluation strategy; and determining a target evaluation report of the target data structure according to the analysis result.
Optionally, the evaluation module at least includes one of: the evaluation card characteristic quantity IV value, the contribution index value of the evaluation card as stability, the evaluation card K-S statistic value and the evaluation card Giyny coefficient value.
Optionally, the determining module is further configured to, when there are a plurality of target evaluation indexes in the target evaluation report, obtain a threshold range of an expected index corresponding to the plurality of target evaluation indexes; when the target evaluation indexes meet the threshold ranges of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report meets preset conditions, and making a decision generated by the strategy analysis module meet requirements; and under the condition that the target evaluation indexes do not meet the threshold range of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report does not meet the preset condition, and resetting the strategy analysis module if the decision generated by the strategy analysis module does not meet the requirement.
Optionally, the apparatus further comprises: and the storage module is used for executing the decision generated by the strategy analysis module and storing the decision data information in a target evaluation report corresponding to the strategy analysis module under the condition that the strategy analysis module is confirmed to meet the preset condition.
According to another embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
According to the invention, a target data structure corresponding to a target object in a strategy analysis module is obtained, wherein the target data structure comprises at least one of the following data: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object; inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained through machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure; by adopting the technical scheme, the problem that the accuracy of the strategy analysis module is reduced and the like in the related technology due to various internal and external factors such as economic environment, change of customer groups, data source acquisition and the like in the related technology is solved, the effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expectation is judged, the analysis strategy of the strategy analysis module is adjusted, and the accuracy of the strategy analysis module under the condition of external condition change is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a block diagram of a hardware configuration of a computer terminal of a method for determining an evaluation index according to an embodiment of the present invention;
fig. 2 is a flowchart of an evaluation index determination method according to an embodiment of the present invention;
FIG. 3 is a consumer finance oriented wind control policy monitoring system according to an alternative embodiment of the present invention;
FIG. 4 is a schematic diagram of a policy monitoring data structure according to an alternative embodiment of the present invention;
FIG. 5 is a schematic diagram of a comprehensive analysis of loan information, in accordance with an alternative embodiment of the invention;
FIG. 6 is a graphical illustration of a Gini coefficient according to an alternative embodiment of the present invention;
fig. 7 is a block diagram of the configuration of an evaluation index determination apparatus according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method provided by the first embodiment of the present application may be executed in a computer terminal or a similar computing device. Taking an example of the method running on a computer terminal, fig. 1 is a hardware structure block diagram of the computer terminal of the determination method of the evaluation index according to the embodiment of the present invention. As shown in fig. 1, a computer terminal may include one or more (only one shown) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to the determination method of the evaluation index in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
An embodiment of the present invention provides a method for determining an evaluation index, which is applied to the above-mentioned computer terminal, and fig. 2 is a flowchart of the method for determining an evaluation index according to the embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, obtaining a target data structure corresponding to a target object, where the target data structure includes at least one of: information of the target object, application information of the target object, escort information of the target object, and decision result information of the target object;
step S204, inputting the target data structure into a policy analysis model to obtain a target characteristic value of the target data structure, wherein the policy analysis model is trained by machine learning using multiple sets of data, and each set of data in the multiple sets of data includes: the target data structure and a target characteristic value corresponding to the target data structure;
step S206, determining whether to provide resources for the target object according to the target characteristic value.
Through the steps, a target data structure corresponding to a target object in the strategy analysis module is obtained, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object; inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained through machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure; by adopting the technical scheme, the problem that the accuracy of the strategy analysis module is reduced and the like in the related technology due to various internal and external factors such as economic environment, change of customer groups, data source acquisition and the like in the related technology is solved, the effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expectation is judged, the analysis strategy of the strategy analysis module is adjusted, and the accuracy of the strategy analysis module under the condition of external condition change is improved.
Optionally, the obtaining of the target data structure corresponding to the target object in the policy analysis module includes: acquiring result information of a target object in the strategy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires a record of resources; and acquiring a target data structure corresponding to the target object from the result information.
In order to ensure that the acquired target data structure of the target object better conforms to the actual financial condition, when the target data structure is acquired, result information of a target event of resources successfully acquired by the target object can be acquired, and therefore the accuracy of the target data structure is ensured.
For example, the information such as the clearing state of the user after the loan is successful is determined, the historical overdue and the current overdue conditions of the user can be evaluated according to the repayment behavior performance of the user, the decision data and the credit repayment performance data can be analyzed in a linkage manner by associating the application number in the application information table with the application number in the loan information table, so that real-time monitoring is realized, the passing rate conditions such as the single number of application, the single number of credit success, the passing rate of credit, the anti-fraud rejection and the like, the average credit line condition, the number of hits, the passing number and the passing rate condition of rejection of each strategy are combined with the credit performance data, flexible diversification analysis and credit repayment performance data tracking are carried out, and the stability and the accuracy of a scoring model are monitored.
Optionally, the policy monitoring model comprises: the method comprises the following steps of inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the evaluation indexes comprise: determining an evaluation strategy corresponding to the target data structure according to the input target data structure, and determining a target evaluation index corresponding to the evaluation strategy from a plurality of target evaluation indexes; analyzing the target data structure through a target evaluation index corresponding to the evaluation strategy; and determining a target evaluation report of the target data structure according to the analysis result.
In short, in order to ensure the pertinence of the policy monitoring model, the data information in the target data structure is determined in advance, the evaluation policy of the target data structure is confirmed, the target evaluation index corresponding to the evaluation policy is determined from a plurality of target evaluation indexes, the data information is analyzed, and the target evaluation report of the target data structure is determined according to the analysis result.
Optionally, the evaluation index includes at least one of: the evaluation card characteristic quantity IV value, the contribution index value of the evaluation card as stability, the evaluation card K-S statistic value and the evaluation card Giyny coefficient value.
Optionally, the determining whether the target evaluation index in the target evaluation report reaches an expected index to determine whether the decision meets a preset condition includes: under the condition that a plurality of target evaluation indexes are contained in the target evaluation report, acquiring threshold value ranges of expected indexes corresponding to the target evaluation indexes; when the target evaluation indexes meet the threshold ranges of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report meets preset conditions, and making a decision generated by the strategy analysis module meet requirements; and under the condition that the target evaluation indexes do not meet the threshold range of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report does not meet the preset condition, and resetting the strategy analysis module if the decision generated by the strategy analysis module does not meet the requirement.
That is, because there may be multiple target evaluation indexes in the target data structure, but the requirements of different target objects for providing resources are different, after obtaining the threshold ranges of multiple expected indexes corresponding to the multiple target evaluation indexes corresponding to the target data structure, further determining the multiple target evaluation indexes, and after determining that all target evaluation indexes satisfy the threshold ranges of the expected indexes, determining that the decision generated by the policy analysis module meets the requirements, and performing smoothly without adjustment. The effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expectation is judged, the analysis strategy of the strategy analysis module is further adjusted, and the accuracy of the strategy analysis module under the condition of external condition change is improved.
Optionally, after determining whether the target evaluation index in the target evaluation report reaches an expected index to determine whether the policy analysis module meets a preset condition, the method further includes: and under the condition that the strategy analysis module is confirmed to meet the preset conditions, executing the decision generated by the strategy analysis module, and storing the decision data information in a target evaluation report corresponding to the strategy analysis module.
In short, after the policy analysis module is determined to meet the preset condition, that is, the accuracy of the policy analysis module meets the application threshold, it is determined that the decision process does not deviate from the expectation, further, according to the judgment result of the policy analysis module, it is determined that resources are provided for the target object or the resources cannot be provided for the target object, the decision data information corresponding to the target object is determined according to the judgment result, when the resources are provided for the target object, reference is made, the time interval of resource release is accelerated, multiple successful records of the target object can be stored, when the process is executed again, processing can be preferentially performed, and the records of the number of times of use of the policy analysis module with effectiveness and the target evaluation report corresponding to the policy analysis module are stored in the database in a one-to-one correspondence manner.
In order to better understand the determination process of the evaluation index, the following description is made with reference to an alternative embodiment, but the invention is not limited to the technical solution of the embodiment of the present invention.
An optional embodiment of the present invention provides a consumption finance-oriented wind control policy monitoring system, including: a strategy monitoring data structure module 32 and a strategy model monitoring analysis module 34. The policy monitoring data structure module 32 contains information data (corresponding to a target data structure in the embodiment of the present invention) that needs to be collected by a user (corresponding to a target object in the embodiment of the present invention) when consuming a financial application; the policy model monitoring and analyzing module 34 is configured to analyze the user information data stored in the policy monitoring data structure module 32 through a monitoring and scoring model (which is equivalent to the policy monitoring model in the embodiment of the present invention), so as to implement monitoring of the credit wind control policy.
It should be noted that, a detailed data structure in the policy monitoring data structure module 32 is shown in fig. 4, and the application information stored in the policy monitoring data structure module 32 includes user information, security information, and decision result information; the decision result information comprises score card return information and trigger rule information, and the score card return information can be correspondingly converted according to corresponding characteristic variable information; in addition, since the decision result is influenced by the derivative variable, the decision result information also includes the derivative variable information. The user information also comprises user credit investigation information, contact information and fraud information, wherein the user credit investigation information comprises user credit investigation information, user credit card credit investigation information and user inquiry information.
Optionally, according to the characteristics of the consumption financial business, a data framework of corresponding decision data is designed by determining input variables and output variables of a decision engine and log data generated by the decision engine in a risk decision making process in a consumption financial wind control decision making process, so that storage and processing of data monitored by a subsequent risk strategy are facilitated, and a foundation is laid for user variation in loan portrait, user asset quality analysis and user behavior analysis.
For example, in the risk decision process, since one application corresponds to one user and one user corresponds to multiple credit records, such as checking out multiple credit cards and multiple loans on the credit investigation of people, checking out the credit investigation records of people or handling multiple loan products inside, the borrower has multiple contacts, and when the decision engine outputs, the loan application may hit multiple rules and the like under a one-to-many condition, a one-to-many hierarchical association relationship needs to be established to support the input and output of the risk decision and the derivative variable data generated in the decision process. When the user finally pays through the risk decision, and the user signs the contract, the consumption financial service institution generates a repayment plan of each period of each contract, which comprises a payback date, a payback fund, a payback interest, a payback penalty, a payback detail, a real payback date, a real payback principal, a real payback interest, a real payback penalty and an exemption information, determines the information of clearing state and the like, and can evaluate the historical overdue and the current overdue condition of the user according to the repayment behavior performance of the user, at the moment, the application number in the application information table and the application number in the loan information table are associated to realize the linkage analysis of decision data and credit repayment performance data, further realize the real-time monitoring, the conditions of passing rates of applying for singular number, successful singular number of credit, passing rate of credit, anti-fraud rejection and the like, the condition of average credit line, the number of the life of each strategy, and the passing number, And the passing rate condition of the rejection number is combined with credit performance data, flexible and diversified analysis and credit repayment performance data tracking are carried out, and the stability of the scoring model is monitored.
As shown in FIG. 5, the stability of the monitoring and scoring model is further ensured by comparing the application information of the user in the application information table with the corresponding customer information recorded in the system and combining the loan information in the system to carry out comprehensive analysis.
Optionally, daily piece feeding amount, checking batch, throughput, loan amount, checking pass rate, approval amount, approval and approval average amount, loan piece average amount are monitored in real time by the system, and a specific table structure is shown in table 1:
TABLE 1
Optionally, the analysis of the rule offending condition included in the decision result information may be performed by taking the rule as a unit, and counting the number of people that a single rule is triggered and the final review result corresponding to the single rule, where a specific table structure may be as shown in table 2:
TABLE 2
It should be noted that when the approval pass rate suddenly decreases, a service person may analyze, through the monitoring report, what cause causes the pass rate to decrease, whether the cause is caused by a rejection rule, and which rule causes the pass rate to decrease, compare and analyze the rejection data distribution occupation ratio of each rule through a policy analysis logic, find out a rule with a higher occupation ratio, analyze a variable (equivalent to a target characteristic value in an embodiment of the present invention) corresponding to the rule, and finally make a wind control policy.
Optionally, the monitoring scoring model corresponds to a scoring card feature quantity IV (information Value, IV) Value analysis report, the feature quantity is a variable corresponding to each scoring card, the scoring model is aimed at distinguishing good customers and bad customers, the bad customers are non-target customers identified by the company, and for example, the historical overdue times exceed the overdue times which are more than the set times. The evaluation card feature quantity IV value analysis report is further expressed by WOE (Weight Of Evidence, abbreviated as WOE) coding, and when WOE coding calculation is performed, grouping processing is required according to the difference Of variables, and after grouping, the calculation formula Of WOE for the ith group is as follows:
pyiis the proportion of default customers of the group to default customers in all samples, pniIs the proportion of non-default customers in the group to non-default customers in all samples. It can also be understood that the difference between the ratio of the default customer to the non-default customer in the group and the ratio in all samples is greater, the greater the WOE, the greater the difference, and the greater the likelihood of a sample default in the group. Further determination based on WOE valueThe IV value is formulated as follows:
and further calculating the IV value of the whole variable, wherein the formula is as follows:
all IV values are added, and in addition, the influence of the number of variables of each packet is considered by the IV values, so that the influence of each packet level can be comprehensively reflected.
Alternatively, the scoring card characteristic quantity IV value analysis report may be as shown in table 3.
TABLE 3
Optionally, the monitoring and scoring model is a Stability analysis report corresponding to a scoring card, where a PS (condition Stability Index, PSI) reflects distribution of the verification sample in each scoring segment and Stability of distribution of the modeling sample. In modeling, we often use to screen for characteristic variables, evaluate model stability. Stability is referenced, so two distributions are required-actual distribution and expected distribution. In modeling, a training Sample (INS) is usually used as an expected distribution, and a verification Sample is usually used as an actual distribution. The verification samples generally include Out of Sample (OOS) and Out of Time (OOT) samples. The calculation formula of PSI is as follows:
wherein: a represents actual reality and E represents expected expectation, and the smaller the PSI value, the smaller the difference between the two distributions, and the more stable the representation. The PSI value ranges and recommendations are shown in table 4 below:
TABLE 4
Optionally, the monitoring scoring model corresponds to a scoring card K-S statistical analysis report, and KS (Kolmogorov-smirnov, abbreviated as KS) is commonly used for evaluating the model discrimination. The greater the degree of discrimination, the stronger the risk ranking ability (ranking ability) of the description model, the fuzzy and continuous definition between the good account (good _ rate) and the bad account (bad _ rate) is always, and depending on the actual business requirements, the KS index tends to measure the difference between the positive and negative sample distributions from the probability perspective. Generally, a larger KS indicates a better degree of positive and negative sample discrimination, as expressed by the following equation:
KS＝max{|cum(bad_rate)-cum(good_rate)|}
alternatively, the scoring card K-S statistical analysis report may be as shown in table 5.
TABLE 5
| Grading mould Model (III) | Scoring Interval(s) | Number of good accounts Eyes of a user | Bad account Number of | Uncertain account Number of | Cumulative good account Number of | Accumulating bad accounts Number of | Account totalizing hundred Ratio of division | Cumulative bad account Ratio of division | Solving for Coefficient of performance | K-S |
Optionally, the monitoring scoring model corresponds to a scoring Cakuni coefficient statistical analysis report, and the GINI coefficient is also used for evaluating the risk discrimination capability of the model. The GINI statistical value measures the area between the cumulative distribution of the bad account number on the good account number and a random distribution curve, and the bigger the difference between the good account number and the bad account number is, the higher the GINI index is, and the stronger the risk distinguishing capability of the model is.
The GINI coefficient is calculated as follows: and calculating the number of good and bad accounts of each scoring interval. And calculating the ratio of the accumulated good account number to the total good account number (accumulated good%) and the ratio of the accumulated bad account number to the total bad account number (accumulated bad%) in each scoring interval. The curve ADC shown in fig. 6 is obtained according to the accumulated good account ratio and the accumulated bad account ratio. Calculating the area of the shadow part, wherein the percentage of the shadow area in the area of the right triangle ABC is the GINI coefficient.
Alternatively, the scoring card K-S statistical analysis report may be as shown in table 6.
TABLE 6
| Grading mould Model (III) | Scoring area Workshop | Number of good accounts Eyes of a user | Number of bad accounts Eyes of a user | Uncertain account Number of | Cumulative good account Number of | Accumulating bad accounts Number of | Account totalizing hundred Ratio of division | Cumulative bad account Ratio of division | System of solution Number of | Keny system Number of |
According to the optional embodiment of the invention, the intelligent wind control strategy needs to be continuously optimized, adjusted, iterated and updated, the complete consumption financial wind control strategy and model system can dynamically monitor the accuracy of the online operating strategy on the credit risk assessment of the user in real time, and the purposes of data driving service, continuous improvement of the wind control strategy and promotion of wind control management differentiation and credit service humanization can be achieved through the analysis of the operation strategy monitoring.
In summary, in the optional embodiment of the present invention, the unstructured log data in the risk process is stored through the table of establishing multi-level parent-child relations such as application information, applicant information, credit investigation information, decision result, scoring return result, trigger rule information, etc. input and output variables of the decision engine and intermediate data generated in the decision process, so as to provide flexible and diversified analysis and credit repayment expression data tracking for wind-controlled real-time monitoring of the passage rate conditions such as application singular number, credit success singular number, credit granting passage rate, anti-fraud rejection, etc., the average credit line condition, the number of hits, the passage number, the number of rejects of each policy, and in combination with the credit expression data, monitor the stability and effectiveness of the scoring model, provide technical data and technical support, and provide approval monitoring for the wind-controlled policies and models, The analysis of the operation strategy model monitoring can achieve the purposes of data driving service, continuous perfection of wind control strategy, promotion of differentiation of wind control management and humanization of credit service, further approach to the scene of consumption financial service, real-time monitoring of strategies and models in the process of actual risk strategy monitoring, direct implementation on the ground, automatic generation of monitoring reports, storage of all data of a decision engine, realization of linkage analysis with repayment expression data, more complete customer portrait analysis, the risk assessment of the credit customer is more accurate.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a device for determining an evaluation index is further provided, and the device is used to implement the foregoing embodiments and preferred embodiments, which have already been described and are not described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 7 is a block diagram showing the configuration of an evaluation index determination apparatus according to an embodiment of the present invention, which includes, as shown in fig. 7:
(1) an obtaining module 72, configured to obtain a target data structure corresponding to a target object in the policy analysis module, where the target data structure includes at least one of: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object;
(2) an evaluation module 74, configured to input the target data structure into a policy monitoring model to obtain a target evaluation report of the target data structure, where the policy monitoring model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: the target data structure and a target evaluation report corresponding to the target data structure;
(3) a determining module 76, configured to determine whether the target evaluation index in the target evaluation report reaches an expected index, so as to determine whether the decision meets a preset condition.
Through the device, a target data structure corresponding to a target object in the strategy analysis module is obtained, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object; inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained through machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure; by adopting the technical scheme, the problem that the accuracy of the strategy analysis module is reduced and the like in the related technology due to various internal and external factors such as economic environment, change of customer groups, data source acquisition and the like in the related technology is solved, the effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expectation is judged, the analysis strategy of the strategy analysis module is adjusted, and the accuracy of the strategy analysis module under the condition of external condition change is improved.
Optionally, the obtaining module is further configured to: the acquisition module is further configured to: acquiring result information of a target object in the strategy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires a record of resources; and acquiring a target data structure corresponding to the target object from the result information.
In order to ensure that the acquired target data structure of the target object better conforms to the actual financial condition, when the target data structure is acquired, result information of a target event of resources successfully acquired by the target object can be acquired, and therefore the accuracy of the target data structure is ensured.
For example, the information such as the clearing state of the user after the loan is successful is determined, the historical overdue and the current overdue conditions of the user can be evaluated according to the repayment behavior performance of the user, the decision data and the credit repayment performance data can be analyzed in a linkage manner by associating the application number in the application information table with the application number in the loan information table, so that real-time monitoring is realized, the passing rate conditions such as the single number of application, the single number of credit success, the passing rate of credit, the anti-fraud rejection and the like, the average credit line condition, the number of hits, the passing number and the passing rate condition of rejection of each strategy are combined with the credit performance data, flexible diversification analysis and credit repayment performance data tracking are carried out, and the stability and the accuracy of a scoring model are monitored.
Optionally, the evaluation module further includes: the evaluation indexes are further used for determining an evaluation strategy corresponding to the target data structure according to the input target data structure and determining a target evaluation index corresponding to the evaluation strategy from a plurality of target evaluation indexes; analyzing the target data structure through a target evaluation index corresponding to the evaluation strategy; and determining a target evaluation report of the target data structure according to the analysis result.
In short, in order to ensure the pertinence of the policy monitoring model, the data information in the target data structure is determined in advance, the evaluation policy of the target data structure is confirmed, the target evaluation index corresponding to the evaluation policy is determined from a plurality of target evaluation indexes, the data information is analyzed, and the target evaluation report of the target data structure is determined according to the analysis result.
Optionally, the evaluation module at least includes one of: the evaluation card characteristic quantity IV value, the contribution index value of the evaluation card as stability, the evaluation card K-S statistic value and the evaluation card Giyny coefficient value.
Optionally, the determining module is further configured to, when there are a plurality of target evaluation indexes in the target evaluation report, obtain a threshold range of an expected index corresponding to the plurality of target evaluation indexes; when the target evaluation indexes meet the threshold ranges of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report meets preset conditions, and making a decision generated by the strategy analysis module meet requirements; and under the condition that the target evaluation indexes do not meet the threshold range of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report does not meet the preset condition, and resetting the strategy analysis module if the decision generated by the strategy analysis module does not meet the requirement.
That is, because there may be multiple target evaluation indexes in the target data structure, but the requirements of different target objects for providing resources are different, after obtaining the threshold ranges of multiple expected indexes corresponding to the multiple target evaluation indexes corresponding to the target data structure, further determining the multiple target evaluation indexes, and after determining that all target evaluation indexes satisfy the threshold ranges of the expected indexes, determining that the decision generated by the policy analysis module meets the requirements, and performing smoothly without adjustment. The effectiveness of the strategy analysis module is analyzed through the strategy monitoring model, whether the decision made by the strategy analysis module deviates from the expectation is judged, the analysis strategy of the strategy analysis module is further adjusted, and the accuracy of the strategy analysis module under the condition of external condition change is improved.
Optionally, the apparatus further comprises: and the storage module is used for executing the decision generated by the strategy analysis module and storing the decision data information in a target evaluation report corresponding to the strategy analysis module under the condition that the strategy analysis module is confirmed to meet the preset condition.
In short, after the policy analysis module is determined to meet the preset condition, that is, the accuracy of the policy analysis module meets the application threshold, it is determined that the decision process does not deviate from the expectation, further, according to the judgment result of the policy analysis module, it is determined that resources are provided for the target object or the resources cannot be provided for the target object, the decision data information corresponding to the target object is determined according to the judgment result, when the resources are provided for the target object, reference is made, the time interval of resource release is accelerated, multiple successful records of the target object can be stored, when the process is executed again, processing can be preferentially performed, and the records of the number of times of use of the policy analysis module with effectiveness and the target evaluation report corresponding to the policy analysis module are stored in the database in a one-to-one correspondence manner.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
An embodiment of the present invention further provides a storage medium including a stored program, wherein the program executes any one of the methods described above.
Alternatively, in the present embodiment, the storage medium may be configured to store program codes for performing the following steps:
s1, acquiring a target data structure corresponding to the target object in the strategy analysis module, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object;
s2, inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained by machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure;
and S3, judging whether the target evaluation index in the target evaluation report reaches an expected index or not, so as to determine whether the decision meets a preset condition or not.
An embodiment of the present invention further provides a storage medium including a stored program, wherein the program executes any one of the methods described above.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring a target data structure corresponding to the target object in the strategy analysis module, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object;
s2, inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained by machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure;
and S3, judging whether the target evaluation index in the target evaluation report reaches an expected index or not, so as to determine whether the decision meets a preset condition or not.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing program codes, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for determining an evaluation index, comprising:
acquiring a target data structure corresponding to a target object in a policy analysis module, wherein the target data structure comprises at least one of the following: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object;
inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the strategy monitoring model is trained through machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: the target data structure and a target evaluation report corresponding to the target data structure;
and judging whether the target evaluation index in the target evaluation report reaches an expected index or not so as to determine whether the decision meets a preset condition or not.
2. The method of claim 1, wherein obtaining a target data structure corresponding to a target object in a policy analysis module comprises:
acquiring result information of a target object in the strategy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires a record of resources;
and acquiring a target data structure corresponding to the target object from the result information.
3. The method of claim 1, wherein the policy monitoring model comprises: the method comprises the following steps of inputting the target data structure into a strategy monitoring model to obtain a target evaluation report of the target data structure, wherein the evaluation indexes comprise:
determining an evaluation strategy corresponding to the target data structure according to the input target data structure, and determining a target evaluation index corresponding to the evaluation strategy from a plurality of target evaluation indexes;
analyzing the target data structure through a target evaluation index corresponding to the evaluation strategy;
and determining a target evaluation report of the target data structure according to the analysis result.
4. The method according to claim 3, wherein the evaluation index includes at least one of:
the evaluation card characteristic quantity IV value, the contribution index value of the evaluation card as stability, the evaluation card K-S statistic value and the evaluation card Giyny coefficient value.
5. The method of claim 1, wherein determining whether the target evaluation index in the target evaluation report reaches an expected index to determine whether the decision meets a preset condition comprises:
under the condition that a plurality of target evaluation indexes are contained in the target evaluation report, acquiring threshold value ranges of expected indexes corresponding to the target evaluation indexes;
when the target evaluation indexes meet the threshold ranges of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report meets preset conditions, and making a decision generated by the strategy analysis module meet requirements;
and under the condition that the target evaluation indexes do not meet the threshold range of the expected indexes, determining that a strategy analysis module corresponding to the target evaluation report does not meet the preset condition, and resetting the strategy analysis module if the decision generated by the strategy analysis module does not meet the requirement.
6. The method of claim 1, wherein after determining whether the target evaluation index in the target evaluation report reaches an expected index to determine whether the policy analysis module meets a preset condition, the method further comprises:
and under the condition that the strategy analysis module is confirmed to meet the preset conditions, executing the decision generated by the strategy analysis module, and storing the decision data information in a target evaluation report corresponding to the strategy analysis module.
7. An apparatus for determining an evaluation index, comprising:
an obtaining module, configured to obtain a target data structure corresponding to a target object in a policy analysis module, where the target data structure includes at least one of: the policy analysis module is used for generating a policy for the target object, wherein the policy is used for indicating whether resources are provided for the target object;
the evaluation module is configured to input the target data structure into a policy monitoring model to obtain a target evaluation report of the target data structure, where the policy monitoring model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: the target data structure and a target evaluation report corresponding to the target data structure;
and the determining module is used for judging whether the target evaluation index in the target evaluation report reaches an expected index so as to determine whether the decision meets a preset condition.
8. The apparatus of claim 7, wherein the obtaining module is further configured to: acquiring result information of a target object in the strategy analysis module after executing a target event, wherein the target event is used for indicating that the target object successfully acquires a record of resources; and acquiring a target data structure corresponding to the target object from the result information.
9. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to carry out the method of any one of claims 1 to 6 when executed.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011403691.1A CN112598225A (en) | 2020-12-04 | 2020-12-04 | Evaluation index determination method and apparatus, storage medium, and electronic apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011403691.1A CN112598225A (en) | 2020-12-04 | 2020-12-04 | Evaluation index determination method and apparatus, storage medium, and electronic apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112598225A true CN112598225A (en) | 2021-04-02 |
Family
ID=75188087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011403691.1A Pending CN112598225A (en) | 2020-12-04 | 2020-12-04 | Evaluation index determination method and apparatus, storage medium, and electronic apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112598225A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113590691A (en) * | 2021-08-04 | 2021-11-02 | 浙江网商银行股份有限公司 | Target object processing method and device |
-
2020
- 2020-12-04 CN CN202011403691.1A patent/CN112598225A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113590691A (en) * | 2021-08-04 | 2021-11-02 | 浙江网商银行股份有限公司 | Target object processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035003A (en) | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning | |
| CN109492945A (en) | Business risk identifies monitoring method, device, equipment and storage medium | |
| CN106651570A (en) | System and method for real-time loan approval | |
| WO2017133456A1 (en) | Method and device for determining risk evaluation parameter | |
| CN109816509A (en) | Generation method, terminal device and the medium of scorecard model | |
| CN111915156B (en) | Service pushing method based on user value, electronic equipment and storage medium | |
| CN111985937A (en) | Method, system, storage medium and computer equipment for evaluating value information of transaction traders | |
| CN113379530A (en) | User risk determination method and device and server | |
| CN111709828A (en) | Resource processing method, device, equipment and system | |
| CN116664012A (en) | Enterprise credit assessment method and system based on big data analysis | |
| CN111061948B (en) | User tag recommendation method and device, computer equipment and storage medium | |
| CN115577152A (en) | Online book borrowing management system based on data analysis | |
| CN114154672A (en) | Data mining method for customer churn prediction | |
| CN112598225A (en) | Evaluation index determination method and apparatus, storage medium, and electronic apparatus | |
| CN113869700A (en) | Performance index prediction method and device, electronic equipment and storage medium | |
| CN109345261A (en) | A kind of credit cost automatic evaluation system | |
| CN113052422A (en) | Wind control model training method and user credit evaluation method | |
| CN116739742A (en) | Monitoring method, device, equipment and storage medium of credit wind control model | |
| CN107844874A (en) | Enterprise operation problem analysis system and its method | |
| CN116228312A (en) | Processing method and device for large-amount point exchange behavior | |
| CN114358519B (en) | Intelligent credit line interest rate adjusting method and device | |
| CN113240259B (en) | Rule policy group generation method and system and electronic equipment | |
| CN110570301B (en) | Risk identification method, device, equipment and medium | |
| CN114581209A (en) | Method, device and equipment for training financial analysis model and storage medium | |
| CN110675240B (en) | Monitoring method and system for risk radar early warning |
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 |