CN117670149A - Passenger group quality scoring method - Google Patents
Passenger group quality scoring method Download PDFInfo
- Publication number
- CN117670149A CN117670149A CN202410143399.2A CN202410143399A CN117670149A CN 117670149 A CN117670149 A CN 117670149A CN 202410143399 A CN202410143399 A CN 202410143399A CN 117670149 A CN117670149 A CN 117670149A
- Authority
- CN
- China
- Prior art keywords
- user
- determining
- information
- approval
- quality score
- 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
- 238000013077 scoring method Methods 0.000 title claims abstract description 20
- 230000008859 change Effects 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000011217 control strategy Methods 0.000 claims abstract description 27
- 238000012795 verification Methods 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 16
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000004220 aggregation Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a guest group quality scoring method, which belongs to the technical field of financial data analysis and specifically comprises the following steps: determining the information similarity of the credit application information of the user and the credit application information of the historical credit application of the user, determining the information quality score of the credit application information of the user by combining the change data of the credit application information of the user, determining the identity information credibility of the user based on the identity verification data of the user, determining the quality score of the user and the user type by combining the information quality score and the approval quality score, determining the classified guest groups of the user by the user type, determining the guest group quality scores of different classified guest groups and the passing rate of matched wind control strategies according to the user data of the classified guest groups, and outputting the approval processing results of the user based on the matched wind control strategies of the classified guest groups.
Description
Technical Field
The invention belongs to the technical field of financial data analysis, and particularly relates to a guest group quality scoring method.
Background
The wind control model and the wind control strategy are core components in the intelligent wind control system. The wind control model outputs a user score, and the wind control strategy decides to take a forward or reverse decision according to the user score. Because the reliability of the credit application information of different users and the passing rate difference of the historical credit application lead to a certain degree of difference of the quality of the users, the users with different quality adopt the same wind control strategy in the prior art, so that the accuracy of the processing result of the credit application of the users is possibly difficult to meet the requirement, and the loan reject ratio of a financial institution is increased.
Aiming at the technical problems, the invention provides a guest group quality scoring method.
Disclosure of Invention
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
according to one aspect of the present invention, a guest group quality scoring method is provided.
The passenger group quality scoring method is characterized by comprising the following steps:
s1, determining an approval processing result of a historical credit application of a user according to an analysis result of a credit report, determining an approval quality score of the user by combining with the approval processing time of the historical credit application of the user, and entering a next step when the user type of the user is determined not to belong to a screening user through the approval quality score;
s2, determining the information similarity between the credit application information of the user and the credit application information of the historical credit application of the user, determining the information quality score of the credit application information of the user by combining the change data of the credit application information of the user, and entering the next step when the user type of the user is determined not to belong to the screening user by the information quality score;
s3, determining the identity information credibility of the user based on the identity verification data of the user, and determining the quality score of the user and the user type of the user by combining the information quality score and the approval quality score;
s4, determining the dividing guest groups of the user through the user types, determining guest group quality scores of different dividing guest groups and the passing rate of the matched wind control strategies according to the user data of the dividing guest groups, and outputting the approval processing result of the user based on the matched wind control strategies of the dividing guest groups.
The invention has the beneficial effects that:
1. the quality score and the user type of the user are determined by combining the identity information credibility, the information quality score and the approval quality score of the user, so that the accurate evaluation of the quality score of the credit application information of the user from multiple angles is realized, the difference of the quality scores of the user caused by the difference of the similarity between the credit application information and the historical credit application information and the difference of the processing results of the historical credit application is considered, the comprehensive evaluation of the quality score of the user is realized by comprehensively considering the reliability of identity verification, and a foundation is laid for the selection of the differentiated realization of the wind control strategy.
2. According to the user data of the divided guest groups, the guest group quality scores of different divided guest groups and the passing rate of the matched wind control strategies are determined, so that the differentiated matching of different wind control strategies based on the difference of the divided guest groups is realized, the passing rate is determined through the guest group quality scores of the divided guest groups, the dynamic adjustment of the passing rate of the wind control strategies from the guest group quality scores is realized, and the accuracy of the approval processing result is further ensured.
The further technical scheme is that the approval processing result comprises approval passing and approval rejection.
The further technical scheme is that the value range of the approval quality score of the user is between 0 and 100, wherein when the approval quality score of the user is larger than a preset score, the user is determined to be a screening user.
The further technical scheme is that the method for determining the identity information credibility of the user comprises the following steps:
and determining an identity verification mode of the user based on the identity verification data of the user, and determining the identity information credibility of the user according to the identity verification mode.
The further technical scheme is that the method for determining the quality scores of the users comprises the following steps:
and determining an information base score of the user based on the information quality score, the weight of the approval quality score and the information base score, and determining the quality score of the user according to the product of the identity information credibility and the information base score.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention as set forth hereinafter.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings;
FIG. 1 is a flow chart of a group quality scoring method;
FIG. 2 is a flow chart of a method of determination of approval quality scores for a user;
FIG. 3 is a flow chart of another method of determination of approval quality scores for a possible user;
FIG. 4 is a flow chart of a method of determining an information quality score for user's credit application information;
FIG. 5 is a flow chart of a method of determining a guest group quality score that divides a guest group;
FIG. 6 is a block diagram of a computer system.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
Because of the approval processing result of the historical credit application of the user, the difference between the credit application information and the historical credit application information, different qualification and the reliability of the information are different to a certain extent, and further the quality scores of different users are different, in the prior art, the same pneumatic control strategy is adopted for different users, for example, the passing rate is the same, but the overdue risk of a customer group with smaller quality score is larger, so that if the different pneumatic control strategy cannot be matched according to the classification result of the customer group, the accurate control of the credit risk may not be realized accurately.
In order to solve the technical problems, the following technical scheme is adopted:
firstly, determining the approval quality score of a user according to the approval result of the historical credit application of the user and the approval time of the historical credit application of the user, specifically determining the approval quality score of the user according to the passing rate of the approval process in the last year, and determining that the user type of the user does not belong to the screening user when the approval quality score is smaller, and entering the next step;
then determining the information quality score of the credit application information of the user according to the information similarity between the credit application information of the user and the credit application information of the historical credit application of the user and the change data of the credit application information of the user, specifically determining the number of the duty ratio of the similar credit application information in the historical credit application and the duty ratio of the change information item of the credit application information of the user and the information quality score, and determining that the user type of the user does not belong to the screening user when the information quality score is smaller, and entering the next step;
then determining the identity information credibility of the user based on the identity verification data of the user, specifically determining the identity information credibility of the user according to the credibility corresponding to the identity verification mode, then determining the quality score of the user according to the identity information credibility, the information quality score, the weight of the approval quality score and the quality score of the user, determining a quality score interval corresponding to the quality score of the user according to the quality score of the user, and determining the user type of the user according to the corresponding quality score interval;
and finally, determining the guest group division of the user through the user type, determining the number of the users dividing the guest group and the quality scores of different users through the user data of the guest group division, determining the guest group quality score of the guest group division according to the number of the users dividing the guest group and the quality scores of different users, and outputting the approval processing result of the users based on the matched wind control strategy of the guest group division.
The following will be described from two perspectives of a method class embodiment and a system class embodiment.
In order to solve the above problem, according to an aspect of the present invention, as shown in fig. 1, there is provided a group quality scoring method, which specifically includes:
s1, determining an approval processing result of a historical credit application of a user according to an analysis result of a credit report, determining an approval quality score of the user by combining with the approval processing time of the historical credit application of the user, and entering a next step when the user type of the user is determined not to belong to a screening user through the approval quality score;
further, the approval processing result comprises approval passing and approval rejection.
Specifically, as shown in fig. 2, the method for determining the approval quality score of the user in the step S1 is as follows:
determining an approval passing application and an approval rejection application based on the approval processing result of the historical credit application of the user;
determining approval passing quality scores of the user according to the number of the approval passing applications of the user and the approval processing time of different approval passing applications, and determining approval rejection quality scores of the user according to the number of the approval rejection applications of the user and the approval processing time of different approval rejection applications;
determining the number of the historical credit applications of the user in preset time according to the application time of the historical credit applications of the user, and determining the recent application aggregation degree of the user by combining the passing rate of the historical credit applications of the user in the preset time;
and determining the approval quality score of the user based on the recent application aggregation degree, the approval rejection quality score and the approval passing quality score of the user.
It can be appreciated that the approval quality score of the user ranges from 0 to 100, wherein when the approval quality score of the user is greater than a preset score, the user is determined to be a screening user.
Specifically, when the approval quality score determines that the user type of the user belongs to the screening user, the user is used as the screening user, and the matched wind control strategy of the user is determined through a preset wind control strategy.
In another possible embodiment, the method for determining the approval quality score of the user in the step S1 is as follows:
determining approval passing applications and approval refusing applications based on approval processing results of the historical credit application of the user, acquiring the number of the approval passing applications when the approval passing rate of the historical credit application of the user is larger than a preset approval passing rate, and determining the user as a screening user when the number of the approval passing applications is larger than the preset application number;
when the number of the approval passing applications is not greater than the preset number of applications or the approval passing rate of the historical credit application of the user is not greater than the preset approval passing rate, determining the approval passing assessment of the credit application of the user according to the number of the approval passing applications and the approval passing rate, and when the approval passing assessment of the credit application of the user is greater than a preset value, determining the user as a screening user;
when the approval passing evaluation value of the credit application of the user is not larger than a preset value, determining the approval passing quality score of the user according to the number of the approval passing application of the user and the approval processing time of different approval passing applications, and when the approval passing quality score of the user is larger than a preset score, determining the user as a screening user;
when the approval passing quality score of the user is not more than a preset score, determining the approval rejecting quality score of the user according to the number of the approval rejecting applications of the user and the approval processing time of different approval rejecting applications, determining the number of the historical credit application of the user in the preset time according to the application time of the historical credit application of the user, and determining the recent application aggregation degree of the user according to the passing rate of the historical credit application of the user in the preset time;
and determining the approval quality score of the user based on the recent application aggregation degree, the approval rejection quality score and the approval passing quality score of the user.
In another possible embodiment, as shown in fig. 3, the method for determining the approval quality score of the user in the step S1 is as follows:
s11, determining approval passing application and approval refusing application based on the approval processing result of the historical credit application of the user, determining the approval passing evaluation quantity of the credit application of the user according to the number of the approval passing application and the approval passing rate, judging whether the approval passing evaluation quantity of the credit application of the user is larger than a preset value, if so, entering the next step, and if not, entering the step S14;
s12, determining approval passing quality scores of the users according to the number of the approval passing applications of the users and the approval processing time of different approval passing applications, judging whether the approval passing quality scores of the users are larger than a preset score, if so, determining that the users are screening users, and if not, entering the next step;
s13, determining the number of historical credit applications of the user in preset time according to the application time of the historical credit applications of the user, determining the recent application aggregation level of the user by combining the passing rate of the historical credit applications of the user in the preset time, judging whether the recent application aggregation level of the user is smaller than the preset aggregation level, if so, determining that the user is a screening user, and if not, entering the next step;
s14, determining the approval quality scores of the users according to the number of the approval and rejection applications of the users and the approval processing time of different approval and rejection applications, and determining the approval quality scores of the users based on the recent application aggregation degree, the approval and rejection quality scores and the approval passing quality scores of the users.
S2, determining the information similarity between the credit application information of the user and the credit application information of the historical credit application of the user, determining the information quality score of the credit application information of the user by combining the change data of the credit application information of the user, and entering the next step when the user type of the user is determined not to belong to the screening user by the information quality score;
specifically, the method for determining the information similarity comprises the following steps:
and determining the information similarity of the credit application information of the user and the credit application information of the historical credit application of the user according to the similar quantity of the information items.
The change data of the credit application information includes the number of change information items and the type of change information items in the information items of the credit application information.
As shown in fig. 4, the method for determining the information quality score of the user' S credit application information in the above step S2 includes:
determining the number of deviation credit applications and the number of similar credit applications in the historical credit applications of the user based on the information similarity, and determining the reference similarity of credit application information of the user by combining the information similarity of different historical credit applications;
determining a change information item in the credit application information of the user and a history credit application inconsistent with the change information item according to the change data, taking the change information item and the history credit application as inconsistent applications, and determining change evaluation values of different change information items according to the number of inconsistent applications of different change information items and the approval processing time of different inconsistent applications;
and determining the information item fluctuation amount of the credit application information based on the quantity of the fluctuation information items of the credit application information and the fluctuation evaluation amounts of different fluctuation information items, and determining the information quality score of the credit application information of the user by combining the reference similarity of the credit application information of the user.
In another possible embodiment, the method for determining the information quality score of the credit application information of the user in the step S2 is:
determining that the user is a screening user when the information similarity determines that no deviation credit application exists in the historical credit application of the user;
when deviation credit application exists, determining the number of similar credit applications in the historical credit applications of the user based on the information similarity, and when the number of the similar credit applications is larger than the preset application number, determining the user as a screening user;
when the number of similar credit applications is not greater than the number of preset applications, the number of deviation credit applications and the number of similar credit applications in the historical credit applications of the user are obtained, the reference similarity of credit application information of the user is determined by combining the information similarity of different historical credit applications, and when the reference similarity is greater than a preset similarity threshold, the user is determined to be a screening user;
when the reference similarity is not greater than a preset similarity threshold, determining a change information item in the credit application information of the user and a history credit application inconsistent with the change information item through the change data, taking the change information item and the history credit application as inconsistent applications, determining change evaluation values of different change information items through the number of the inconsistent applications of the different change information items and the approval processing time of the different inconsistent applications, and determining that the user is a screening user when the change information item which does not meet the requirement of the change evaluation value does not exist;
when the fluctuation estimated quantity does not meet the required fluctuation information items, the information item fluctuation quantity of the credit application information is determined based on the quantity of the fluctuation information items of the credit application information and the fluctuation estimated quantity of different fluctuation information items, and the information quality score of the credit application information of the user is determined by combining the reference similarity of the credit application information of the user.
In another possible embodiment, the method for determining the information quality score of the credit application information of the user in the step S2 is:
s21, determining a change information item in the credit application information of the user and a history credit application inconsistent with the change information item according to the change data, taking the change information item and the history credit application as an inconsistent application, determining change evaluation values of different change information items according to the quantity of inconsistent applications of different change information items and the approval processing time of different inconsistent applications, judging whether the change information items of which the change evaluation values do not meet the requirements exist, if so, entering a step S23, and if not, entering a next step;
s22, determining deviation credit application and similar credit application in the historical credit application of the user based on the information similarity, judging whether the number of the similar credit applications is larger than the preset application number, if so, determining that the user is a screening user, and if not, entering the next step;
s23, acquiring the number of deviation credit applications and the number of similar credit applications in the historical credit applications of the user, determining the reference similarity of credit application information of the user by combining the information similarity of different historical credit applications, judging whether the reference similarity is larger than a preset similarity threshold, if so, determining that the user is a screening user, and if not, entering the next step;
s24, determining the fluctuation amount of the information items of the credit application information based on the quantity of the fluctuation information items of the credit application information and the fluctuation estimated amounts of different fluctuation information items, and determining the information quality score of the credit application information of the user by combining the reference similarity of the credit application information of the user.
S3, determining the identity information credibility of the user based on the identity verification data of the user, and determining the quality score of the user and the user type of the user by combining the information quality score and the approval quality score;
it should be noted that, the method for determining the identity information credibility of the user includes:
and determining an identity verification mode of the user based on the identity verification data of the user, and determining the identity information credibility of the user according to the identity verification mode. And determining a quality score for the user and a user type for the user in combination with the information quality score and the approval quality score
Specifically, the method for determining the quality score of the user comprises the following steps:
and determining an information base score of the user based on the information quality score, the weight of the approval quality score and the information base score, and determining the quality score of the user according to the product of the identity information credibility and the information base score.
It can be understood that the method for determining the user type of the user is as follows:
and determining a quality scoring interval corresponding to the quality score of the user according to the quality score of the user, and determining the user type of the user according to the corresponding quality scoring interval.
Specifically, the user types of the users include risk users, information unreliable users and information reliable users.
S4, determining the dividing guest groups of the user through the user types, determining guest group quality scores of different dividing guest groups and the passing rate of the matched wind control strategies according to the user data of the dividing guest groups, and outputting the approval processing result of the user based on the matched wind control strategies of the dividing guest groups.
Specifically, the method for determining the guest group quality score for dividing the guest group includes:
and determining the quantity of the users dividing the guest groups and the quality scores of different users through the user data dividing the guest groups, and determining the guest group quality scores of the guest groups according to the quantity of the users dividing the guest groups and the quality scores of different users.
In another possible embodiment, as shown in fig. 5, the method for determining the guest group quality score of the guest group in step S1 is as follows:
determining the number of users dividing the guest group and the quality scores of different users through the user data dividing the guest group, and determining the reference quality score of the guest group based on the average value of the quality scores of the different users and the number of the users;
determining the quality score deviation amount of different users according to the quality scores of the users and the average value of the quality scores of the different users dividing the guest groups, judging whether the quality score deviation amount is greater than a preset deviation user, if so, entering the next step, and if not, taking the reference quality score as the guest group quality score dividing the guest groups;
determining deviation users in the users dividing the guest groups based on the quality score deviation amount, judging whether the number of the deviation users meets the requirement, if so, taking the reference quality score as the guest group quality score of the guest groups, and if not, entering the next step;
and obtaining the number of the deviation users, determining a guest group quality score correction amount by combining the quality score deviation amounts of different deviation users, and determining the guest group quality score for dividing the guest groups through the guest group quality score correction amount and the reference quality score.
It should be noted that, the passing rate is determined according to the guest group quality score of the divided guest group, where the greater the guest group quality score of the divided guest group is, the higher the passing rate is.
Further, the wind control strategy is constructed through a model based on a machine learning algorithm, wherein the input quantity of the model is the quality score of a user and the user score output by the wind control model, and the output quantity is the approval processing result of the user.
In another aspect, as shown in FIG. 6, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: the processor executes a group quality scoring method as described above when running the computer program.
The above-mentioned guest group quality scoring method specifically includes:
determining approval passing applications and approval refusing applications based on approval processing results of the historical credit application of the user, acquiring the number of the approval passing applications when the approval passing rate of the historical credit application of the user is larger than a preset approval passing rate, and determining the user as a screening user when the number of the approval passing applications is larger than the preset application number;
when the number of the approval passing applications is not greater than the preset number of applications or the approval passing rate of the historical credit application of the user is not greater than the preset approval passing rate, determining the approval passing assessment of the credit application of the user according to the number of the approval passing applications and the approval passing rate, and when the approval passing assessment of the credit application of the user is greater than a preset value, determining the user as a screening user;
when the approval passing evaluation value of the credit application of the user is not larger than a preset value, determining the approval passing quality score of the user according to the number of the approval passing application of the user and the approval processing time of different approval passing applications, and when the approval passing quality score of the user is larger than a preset score, determining the user as a screening user;
when the approval passing quality score of the user is not more than a preset score, determining the approval rejecting quality score of the user according to the number of the approval rejecting applications of the user and the approval processing time of different approval rejecting applications, determining the number of the historical credit application of the user in the preset time according to the application time of the historical credit application of the user, and determining the recent application aggregation degree of the user according to the passing rate of the historical credit application of the user in the preset time;
determining approval quality scores of the users based on the recent application aggregation degree, approval rejection quality scores and approval passing quality scores of the users, and entering the next step when the user types of the users are determined not to belong to screening users through the approval quality scores;
determining the information similarity of the credit application information of the user and the credit application information of the historical credit application of the user, determining the information quality score of the credit application information of the user by combining the change data of the credit application information of the user, and entering the next step when the user type of the user is determined not to belong to the screening user by the information quality score;
determining the identity information credibility of the user based on the identity verification data of the user, and determining the quality score of the user and the user type of the user by combining the information quality score and the approval quality score;
determining a dividing guest group of the user through a user type, determining the number of the users dividing guest group and the quality scores of different users through user data of the dividing guest group, and determining a reference quality score of the dividing guest group based on an average value of the quality scores of the different users and the number of the users;
determining the quality score deviation amount of different users according to the quality scores of the users and the average value of the quality scores of the different users dividing the guest groups, judging whether the quality score deviation amount is greater than a preset deviation user, if so, entering the next step, and if not, taking the reference quality score as the guest group quality score dividing the guest groups;
determining deviation users in the users dividing the guest groups based on the quality score deviation amount, judging whether the number of the deviation users meets the requirement, if so, taking the reference quality score as the guest group quality score of the guest groups, and if not, entering the next step;
the number of the deviation users is obtained, the quality score correction amount of the guest group is determined by combining the quality score deviation amounts of different deviation users, the guest group quality score of the guest group is determined through the guest group quality score correction amount and the reference quality score, the passing rate of the matched wind control strategy is determined, and the approval processing result of the users is output based on the matched wind control strategy of the guest group.
Through the above embodiments, the present invention has the following beneficial effects:
1. the quality score and the user type of the user are determined by combining the identity information credibility, the information quality score and the approval quality score of the user, so that the accurate evaluation of the quality score of the credit application information of the user from multiple angles is realized, the difference of the quality scores of the user caused by the difference of the similarity between the credit application information and the historical credit application information and the difference of the processing results of the historical credit application is considered, the comprehensive evaluation of the quality score of the user is realized by comprehensively considering the reliability of identity verification, and a foundation is laid for the selection of the differentiated realization of the wind control strategy.
2. According to the user data of the divided guest groups, the guest group quality scores of different divided guest groups and the passing rate of the matched wind control strategies are determined, so that the differentiated matching of different wind control strategies based on the difference of the divided guest groups is realized, the passing rate is determined through the guest group quality scores of the divided guest groups, the dynamic adjustment of the passing rate of the wind control strategies from the guest group quality scores is realized, and the accuracy of the approval processing result is further ensured.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (10)
1. The passenger group quality scoring method is characterized by comprising the following steps:
determining the approval processing result of the historical credit application of the user according to the analysis result of the credit report, determining the approval quality score of the user by combining the approval processing time of the historical credit application of the user, and entering the next step when the user type of the user is determined not to belong to the screening user through the approval quality score;
determining the information similarity of the credit application information of the user and the credit application information of the historical credit application of the user, determining the information quality score of the credit application information of the user by combining the change data of the credit application information of the user, and entering the next step when the user type of the user is determined not to belong to the screening user by the information quality score;
determining the identity information credibility of the user based on the identity verification data of the user, and determining the quality score of the user and the user type of the user by combining the information quality score and the approval quality score;
determining the dividing guest groups of the users through the user types, determining guest group quality scores of different dividing guest groups and the passing rate of the matched wind control strategies according to the user data of the dividing guest groups, and outputting the approval processing results of the users based on the matched wind control strategies of the dividing guest groups.
2. A guest group quality scoring method according to claim 1, wherein the approval process results include approval passing, approval rejection.
3. A guest group quality scoring method according to claim 1, wherein the method of determining the approval quality score of the user is:
determining an approval passing application and an approval rejection application based on the approval processing result of the historical credit application of the user;
determining approval passing quality scores of the user according to the number of the approval passing applications of the user and the approval processing time of different approval passing applications, and determining approval rejection quality scores of the user according to the number of the approval rejection applications of the user and the approval processing time of different approval rejection applications;
determining the number of the historical credit applications of the user in preset time according to the application time of the historical credit applications of the user, and determining the recent application aggregation degree of the user by combining the passing rate of the historical credit applications of the user in the preset time;
and determining the approval quality score of the user based on the recent application aggregation degree, the approval rejection quality score and the approval passing quality score of the user.
4. A guest group quality scoring method according to claim 3, wherein the user's approval quality score ranges from 0 to 100, wherein when the user's approval quality score is greater than a predetermined score, the user is determined to be a screening user.
5. A group quality scoring method as recited in claim 1, wherein the information similarity determination method comprises:
and determining the information similarity of the credit application information of the user and the credit application information of the historical credit application of the user according to the similar quantity of the information items.
6. A guest group quality scoring method according to claim 1, wherein the change data of the credit application information includes the number of change information items and the type of change information items in the information items of the credit application information.
7. A group quality scoring method as recited in claim 1, wherein the determining of the information quality score of the user's credit application information comprises:
determining the number of deviation credit applications and the number of similar credit applications in the historical credit applications of the user based on the information similarity, and determining the reference similarity of credit application information of the user by combining the information similarity of different historical credit applications;
determining a change information item in the credit application information of the user and a history credit application inconsistent with the change information item according to the change data, taking the change information item and the history credit application as inconsistent applications, and determining change evaluation values of different change information items according to the number of inconsistent applications of different change information items and the approval processing time of different inconsistent applications;
and determining the information item fluctuation amount of the credit application information based on the quantity of the fluctuation information items of the credit application information and the fluctuation evaluation amounts of different fluctuation information items, and determining the information quality score of the credit application information of the user by combining the reference similarity of the credit application information of the user.
8. A group quality scoring method as recited in claim 1, wherein the determining of the confidence level of the identity information of the user is:
and determining an identity verification mode of the user based on the identity verification data of the user, determining the identity information credibility of the user according to the identity verification mode, and determining the quality score of the user and the user type of the user by combining the information quality score and the approval quality score.
9. A method of guest group quality scoring as recited in claim 1, wherein the method of determining guest group quality scores for the partitioned guest groups is:
determining the number of users dividing the guest group and the quality scores of different users through the user data dividing the guest group, and determining the reference quality score of the guest group based on the average value of the quality scores of the different users and the number of the users;
determining the quality score deviation amount of different users according to the quality scores of the users and the average value of the quality scores of the different users dividing the guest groups, judging whether the quality score deviation amount is greater than a preset deviation user, if so, entering the next step, and if not, taking the reference quality score as the guest group quality score dividing the guest groups;
determining deviation users in the users dividing the guest groups based on the quality score deviation amount, judging whether the number of the deviation users meets the requirement, if so, taking the reference quality score as the guest group quality score of the guest groups, and if not, entering the next step;
and obtaining the number of the deviation users, determining a guest group quality score correction amount by combining the quality score deviation amounts of different deviation users, and determining the guest group quality score for dividing the guest groups through the guest group quality score correction amount and the reference quality score.
10. A guest group quality scoring method according to claim 1, wherein the pass rate is determined based on guest group quality scores of the partitioned guest groups, wherein the greater the guest group quality score of the partitioned guest groups, the higher the pass rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410143399.2A CN117670149A (en) | 2024-02-01 | 2024-02-01 | Passenger group quality scoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410143399.2A CN117670149A (en) | 2024-02-01 | 2024-02-01 | Passenger group quality scoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117670149A true CN117670149A (en) | 2024-03-08 |
Family
ID=90086687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410143399.2A Pending CN117670149A (en) | 2024-02-01 | 2024-02-01 | Passenger group quality scoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117670149A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118035322A (en) * | 2024-04-11 | 2024-05-14 | 浙江之科智慧科技有限公司 | Auxiliary intelligent auditing method and system based on rule base |
| CN118211040A (en) * | 2024-05-17 | 2024-06-18 | 全拓科技(杭州)股份有限公司 | Data quality evaluation analysis method for big data analysis |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6088686A (en) * | 1995-12-12 | 2000-07-11 | Citibank, N.A. | System and method to performing on-line credit reviews and approvals |
| US20180040007A1 (en) * | 2016-08-08 | 2018-02-08 | The Dun & Bradstreet Corporation | Trusted platform and integrated bop applications for networking bop components |
| US20180204280A1 (en) * | 2017-01-17 | 2018-07-19 | Fair Ip, Llc | Rules/Model-Based Data Processing System and Method for User Approval Using Data from Distributed Sources |
| WO2020077888A1 (en) * | 2018-10-16 | 2020-04-23 | 深圳壹账通智能科技有限公司 | Method and apparatus for calculating credit score of loan user, and computer device |
| KR20200090557A (en) * | 2019-01-21 | 2020-07-29 | 신한카드 주식회사 | Apparatus and method for credit rating |
| CN112200656A (en) * | 2020-09-17 | 2021-01-08 | 中国建设银行股份有限公司 | On-line pre-approval method, device, medium and electronic equipment for house loan |
| CN116797357A (en) * | 2023-08-24 | 2023-09-22 | 杭银消费金融股份有限公司 | Financial terminal-based credit authorization processing method and equipment |
| CN116976492A (en) * | 2023-06-08 | 2023-10-31 | 重庆富民银行股份有限公司 | Wind control strategy comparison optimization management system and method |
| CN117132001A (en) * | 2023-10-24 | 2023-11-28 | 杭银消费金融股份有限公司 | Multi-target wind control strategy optimization method and system |
| CN117408805A (en) * | 2023-12-15 | 2024-01-16 | 杭银消费金融股份有限公司 | Credit wind control method and system based on stability modeling |
-
2024
- 2024-02-01 CN CN202410143399.2A patent/CN117670149A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6088686A (en) * | 1995-12-12 | 2000-07-11 | Citibank, N.A. | System and method to performing on-line credit reviews and approvals |
| US20180040007A1 (en) * | 2016-08-08 | 2018-02-08 | The Dun & Bradstreet Corporation | Trusted platform and integrated bop applications for networking bop components |
| US20180204280A1 (en) * | 2017-01-17 | 2018-07-19 | Fair Ip, Llc | Rules/Model-Based Data Processing System and Method for User Approval Using Data from Distributed Sources |
| WO2020077888A1 (en) * | 2018-10-16 | 2020-04-23 | 深圳壹账通智能科技有限公司 | Method and apparatus for calculating credit score of loan user, and computer device |
| KR20200090557A (en) * | 2019-01-21 | 2020-07-29 | 신한카드 주식회사 | Apparatus and method for credit rating |
| CN112200656A (en) * | 2020-09-17 | 2021-01-08 | 中国建设银行股份有限公司 | On-line pre-approval method, device, medium and electronic equipment for house loan |
| CN116976492A (en) * | 2023-06-08 | 2023-10-31 | 重庆富民银行股份有限公司 | Wind control strategy comparison optimization management system and method |
| CN116797357A (en) * | 2023-08-24 | 2023-09-22 | 杭银消费金融股份有限公司 | Financial terminal-based credit authorization processing method and equipment |
| CN117132001A (en) * | 2023-10-24 | 2023-11-28 | 杭银消费金融股份有限公司 | Multi-target wind control strategy optimization method and system |
| CN117408805A (en) * | 2023-12-15 | 2024-01-16 | 杭银消费金融股份有限公司 | Credit wind control method and system based on stability modeling |
Non-Patent Citations (3)
| Title |
|---|
| HUBERT TCHAKOUTE-TCHUIGOUA: "he effect of loan approval decentralization on microfinance institutions\' outreach and loan portfolio qualit", 《JOURNAL OF BUSINESS RESEARCH》, vol. 94, 31 January 2019 (2019-01-31) * |
| 中国工商银行江苏省分行课题组;岳小勇;: "商业银行授信审批的大数据应用模式研究", 《金融纵横》, no. 9, 25 September 2017 (2017-09-25) * |
| 周皓: "金融零售支付风险控制的现状、挑战与对策研究", 《中国工程科学》, vol. 22, no. 6, 31 December 2020 (2020-12-31) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118035322A (en) * | 2024-04-11 | 2024-05-14 | 浙江之科智慧科技有限公司 | Auxiliary intelligent auditing method and system based on rule base |
| CN118211040A (en) * | 2024-05-17 | 2024-06-18 | 全拓科技(杭州)股份有限公司 | Data quality evaluation analysis method for big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117670149A (en) | Passenger group quality scoring method | |
| CN110111113B (en) | Abnormal transaction node detection method and device | |
| CN111723946A (en) | Federal learning method and device applied to block chain | |
| CN109583966A (en) | A kind of high value customer recognition methods, system, equipment and storage medium | |
| US20150262184A1 (en) | Two stage risk model building and evaluation | |
| US11250368B1 (en) | Business prediction method and apparatus | |
| CN108320112B (en) | Method and device for determining health state of equipment | |
| CN117035985A (en) | Trusted overdue risk control method and system | |
| CN112561691A (en) | Customer credit prediction method, device, equipment and storage medium | |
| Khemakhem et al. | Artificial intelligence for credit risk assessment: Artificial neural network and support vector machines | |
| CN117333290B (en) | Integrated multi-scale wind control model construction method | |
| CN111652430A (en) | Internet financial platform default rate prediction method and system | |
| US20220207420A1 (en) | Utilizing machine learning models to characterize a relationship between a user and an entity | |
| Karasev | Monitoring and crediting process control with use of logical and probabilistic risk model | |
| CN107274043B (en) | Quality evaluation method and device of prediction model and electronic equipment | |
| CN113344692A (en) | Method for establishing network loan credit risk assessment model with multi-information-source fusion | |
| CN111104978B (en) | Training method and device for anti-fraud model | |
| KR102105276B1 (en) | System and method for classifying payments based on reinforcement learning | |
| CN109145207B (en) | Information personalized recommendation method and device based on classification index prediction | |
| CN108305174B (en) | Resource processing method, device, storage medium and computer equipment | |
| Hasan | Development of a credit scoring model for retail loan granting financial institutions from frontier markets | |
| CN113763153A (en) | Bank credit risk analysis method and device | |
| Pradnyana et al. | Loan Default Prediction in Microfinance Group Lending with Machine Learning | |
| US20190295177A1 (en) | System and method of cryptocurrency asset allocation via an economy's information processing cycle | |
| CN117709906B (en) | External data source query decision method and device |
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 |