CN112598422A - Transaction risk assessment method, system, device and storage medium - Google Patents

Transaction risk assessment method, system, device and storage medium Download PDF

Info

Publication number
CN112598422A
CN112598422A CN202011537443.6A CN202011537443A CN112598422A CN 112598422 A CN112598422 A CN 112598422A CN 202011537443 A CN202011537443 A CN 202011537443A CN 112598422 A CN112598422 A CN 112598422A
Authority
CN
China
Prior art keywords
transaction
rule
index
initial
data
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
Application number
CN202011537443.6A
Other languages
Chinese (zh)
Inventor
季德志
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202011537443.6A priority Critical patent/CN112598422A/en
Publication of CN112598422A publication Critical patent/CN112598422A/en
Pending legal-status Critical Current

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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Databases & Information Systems (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Technology Law (AREA)
  • Computer Security & Cryptography (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The embodiment of the invention provides a transaction event risk assessment method, which comprises the following steps: acquiring historical transaction flow data; analyzing the historical transaction flow data to obtain transaction attribute indexes corresponding to the historical transaction flow data, index data corresponding to the transaction attribute indexes and categories corresponding to the index data; generating an initial rule based on the transaction attribute index, index data corresponding to the transaction attribute index and a category corresponding to the index data; refining the initial rule to obtain a final rule; generating a transaction risk evaluation strategy according to the final rule; and evaluating the transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event. The invention can improve the accuracy and efficiency of real-time transaction risk assessment.

Description

Transaction risk assessment method, system, device and storage medium
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a transaction risk assessment method, a system, equipment and a storage medium.
Background
In the course of financial transaction, for example, in the course of loan of individual and enterprise, some risk transactions occur, and since the transactions involve a lot of data, the risk of the transactions is judged manually according to the data, which is not only inefficient, but also prone to errors.
Disclosure of Invention
In view of this, embodiments of the present invention provide a transaction event risk assessment method, system, computer device and computer-readable storage medium, which are used to solve the problems of low transaction risk assessment efficiency and low accuracy.
The embodiment of the invention solves the technical problems through the following technical scheme:
a transaction event risk assessment method, comprising:
acquiring historical transaction flow data;
analyzing the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index and a category corresponding to the index data;
generating an initial rule based on the transaction attribute index, index data corresponding to the transaction attribute index and a category corresponding to the index data, wherein the initial rule comprises a rule front piece and a rule back piece, the rule front piece is a set formed by N conjuncts formed by the transaction attribute index and the index data corresponding to the transaction attribute index, and N is an integer greater than or equal to 0; the rule back part is a category determined by the conjuncts;
refining the initial rule to obtain a final rule;
extracting a plurality of key evaluation fields from the final rule, and filling the key evaluation fields into a preset transaction risk evaluation template to generate a transaction risk evaluation strategy;
and evaluating the transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
Further, the analyzing the historical transaction flow data to obtain the transaction attribute index corresponding to the historical transaction flow data, the index data corresponding to the transaction attribute index, and the category corresponding to the index data includes:
performing logic calculation on the historical transaction flow data according to a preset rule to obtain historical derivative transaction flow data;
performing attribute classification on the historical derived transaction flow data to obtain transaction attribute indexes and index data corresponding to the transaction attribute indexes;
and dividing the historical derived transaction flow data into corresponding categories according to the transaction attribute indexes and the index data.
Further, the rule front part of the initial rule is an empty set with the number of conjuncts being 0; the refinement of the initial rule to obtain a final rule comprises:
adding conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition;
and iterating the initial rules meeting the preset conditions to obtain final rules.
Further, the refining the initial rule until the initial rule meets a preset condition includes:
and stopping refining the initial rule when the rule back part obtained according to the conjunction items added in the rule front part cannot meet the preset condition.
Further, a rule capable of correctly predicting the category is randomly determined to be an initial rule, a rule front piece of the initial rule comprises M conjunctions, wherein M is an integer greater than 1; the refinement of the initial rule by the basis to obtain a final rule comprises:
deleting conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition;
and iterating the initial rules meeting the preset conditions to obtain final rules.
Further, the refining the initial rule until the initial rule meets a preset condition includes:
the preset condition is that the rule back-piece starts to cover a counter-example, and the counter-example is a category which cannot be determined by the rule front-piece of the initial rule.
Further, the evaluating the transaction event according to the transaction risk evaluation policy to obtain a risk evaluation result of the transaction event includes:
acquiring transaction flow data of a transaction event;
performing logic calculation on the transaction flow data according to a preset rule to obtain derivative transaction flow data;
and evaluating the derived transaction running data according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
In order to achieve the above object, an embodiment of the present invention further provides a transaction event risk assessment system, including:
the data acquisition module is used for acquiring historical transaction flow data;
the data processing module is used for analyzing the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index and a category corresponding to the index data;
a rule generating module, configured to generate an initial rule based on the transaction attribute index, the index data corresponding to the transaction attribute index, and the category corresponding to the index data, where the initial rule includes a rule front part and a rule back part, the rule front part is a set formed by N conjunctions formed by the transaction attribute index and the index data corresponding to the transaction attribute index, and N is an integer greater than or equal to 0; the rule back part is a category determined by the conjuncts;
the rule generating module is further configured to refine the initial rule to obtain a final rule;
the strategy generation module is used for extracting a plurality of key evaluation fields from the final rule and filling the key evaluation fields into a preset transaction risk evaluation template so as to generate a transaction risk evaluation strategy;
and the evaluation module is used for evaluating the transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
In order to achieve the above object, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the transaction event risk assessment method as described above when executing the computer program.
To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, where the computer program is executable by at least one processor to cause the at least one processor to execute the steps of the transaction event risk assessment method as described above.
According to the transaction event risk assessment method, the transaction event risk assessment system, the computer equipment and the computer readable storage medium, historical transaction flow data are obtained; analyzing the historical transaction flow data to obtain transaction attribute indexes corresponding to the historical transaction flow data, index data corresponding to the transaction attribute indexes and categories corresponding to the index data; generating an initial rule based on the transaction attribute index, the index data corresponding to the transaction attribute index and the category corresponding to the index data, and refining the initial rule to obtain a final rule; generating a transaction risk evaluation strategy according to the final rule; and evaluating the real-time transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event, so that the efficiency and the accuracy of transaction risk evaluation are improved.
The invention is described in detail below with reference to the drawings and specific examples, but the invention is not limited thereto.
Drawings
FIG. 1 is a flowchart illustrating a method for risk assessment of transaction events according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating steps of a method for analyzing the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index, and a category corresponding to the index data according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps of a method for refining the initial rule to obtain a final rule according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating steps of a method for refining the initial rule to obtain a final rule according to another embodiment of the present invention;
FIG. 5 is a flowchart illustrating a method for evaluating a transaction event according to the transaction risk evaluation policy to obtain a risk evaluation result of the transaction event according to an embodiment of the present invention;
FIG. 6 is a block diagram of a transaction event risk assessment system according to a second embodiment of the present invention;
fig. 7 is a schematic hardware structure diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Technical solutions between various embodiments may be combined with each other, but must be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Example one
Referring to fig. 1, a flowchart illustrating steps of a transaction event risk assessment method according to an embodiment of the invention is shown. It is to be understood that the flow charts in the embodiments of the present method are not intended to limit the order in which the steps are performed. The following description is given by taking a computer device as an execution subject, specifically as follows:
as shown in fig. 1, the transaction event risk assessment method may include steps S100 to S600, in which:
and step S100, acquiring historical transaction flow data.
Specifically, the historical transaction flow data refers to data generated by a user during a transaction process, such as a transaction date, a transaction time, a transaction card number, a transaction account number, a region number, a website number, a location, a terminal number, a teller number, a transaction certificate, a transaction channel, and the like.
In an exemplary embodiment, historical transaction flow data is obtained via sql (structured query language) from business databases including, but not limited to: a relational database, a distributed search engine database, and a cache database. The historical transaction flow data refers to business data generated based on a business layer.
Step S200, analyzing the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index and a category corresponding to the index data.
In an exemplary embodiment, the transaction attribute metrics of the historical transaction pipeline data include transaction attribute metrics of a plurality of categories, such as an amount category, a quantity category, and a proportion category; the transaction attribute indexes of the amount category include various principal, interest, balance and the like, for example, remaining principal, loan balance, overdue penalty, overdue interest, default principal and the like. The transaction attribute indexes of the quantity category include various types of numbers, accounts, numbers of pieces and the like, for example, application number, deposit number, daily average quantity of pieces, settlement account number and the like. Transaction attribute metrics for the ratio class include class occupancy, ratio, etc., for example: passage rate, overdue rate, reject rate, suspected fraud rate, etc. The corresponding index data refers to the historical transaction flow data which is processed to obtain the corresponding index data. Categories refer to categories that are determined according to the transaction attribute metrics, such as "high risk", "low risk", and "medium risk", among others. For example, when the fraction defective is ≧ 20%, the category is medium risk.
In an exemplary embodiment, referring to fig. 2, step S200 may further include:
step S201, performing logic calculation on the historical transaction running data according to a preset rule to obtain historical derivative transaction running data.
The derived transaction flow data refers to data derived by performing secondary calculation by using a preset rule based on the historical transaction flow data, for example: the loan application number is historical transaction flow data, and the average loan application number is derivative transaction flow data.
In detail, the logic calculation of the historical transaction flow data according to the preset rule to obtain derivative transaction flow data includes:
and inputting the historical transaction flow data into a preset calculation formula to obtain the derivative transaction flow data.
And the preset calculation formula can be selected and set by a developer in a self-defined way according to the requirement of the generation rule. For example: the historical transaction running data is the number of loan application strokes, the derivative transaction running data is the average number of loan application strokes per month, and the derivative running data of the number of loan application strokes per month can be obtained for n/12 through a calculation formula, wherein n is the number of loan application strokes per year.
Step S202, attribute classification is carried out on the historical derived transaction flow data to obtain transaction attribute indexes and index data corresponding to the transaction attribute indexes.
Specifically, the index data is data used for classifying the historical derived transaction flow data, and the index data is determined according to the attribute of the historical derived transaction flow. For example, the index data may be obtained by dividing the determined index data into an average number of loan applications per month of 3-5, 3-10, 10 or more, based on the average number of loan applications per month.
Step S203, according to the transaction attribute indexes and the index data, dividing the historical derived transaction running data to obtain categories corresponding to the index data.
Specifically, when the index data is determined to be 3-5, 3-10, 10 or more, the derivative transaction chronological data is correspondingly divided into "low risk", "medium risk", and "high risk" according to the index data, for example, taking the index data as the average number of loan applications per month as an example, when the derivative transaction chronological data is the average number of loan applications per month as 3, the category of the derivative transaction chronological data is determined to be low risk.
Step S300, generating an initial rule based on the transaction attribute index, the index data corresponding to the transaction attribute index and the category corresponding to the index data, wherein the initial rule comprises a rule front piece and a rule back piece, the rule front piece is a set formed by N conjuncts formed by the transaction attribute index and the index data corresponding to the transaction attribute index, and N is an integer greater than or equal to 0; the rule back-part is the category determined by the conjuncts.
In an exemplary embodiment, the rules may be expressed in the form:
ri (condition i) → yi;
the left side ri of the rule (condition i) is the rule antecedent or precondition. ri is the conjunction of the transaction attribute metrics, i.e., all transaction attribute metrics in the rule (condition i) are satisfied simultaneously.
The condition i ═ a1 op v1 ^ (a2 op v2) ^ … ^ (Aj op vj);
wherein (Aj, vj) is a transaction attribute index-value pair, the value pair is a value corresponding to the transaction attribute index, for example, the transaction attribute index is "suspected fraud rate", the value pair is 10%, op is a comparison operator, and is selected from the set { ═ not, <, > larger, ≦ and ≧ represents a parallel relationship. Each transaction attribute index-value pair (ajop vj) is referred to as a conjunction. The rule right is called the rule back-piece and contains the prediction class yi. For example, a rule r1 ≧ 10000 ≧ 100000 ≧ high risk, and a rule indicating that the overdue penalty of the transaction body is 10000 or more and the default principal is 100000 or more determines that the transaction is a high risk transaction.
And S400, refining the initial rule to obtain a final rule.
In an exemplary embodiment, assume that the rule antecedent of the generated initial rule is an empty set with a number of conjuncts of 0; and refining the initial rule to obtain a final rule. Referring to fig. 3, step S400 may further include:
step S401A, adding conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition.
Specifically, the initial rule with the rule front-part conjunctive item number of 0 is as follows: r { } → y, where the left side of the rule is an empty set and the right side of the rule contains the target class. The initial rule is of poor quality because it covers all classes because it is an empty set to the right.
In an exemplary embodiment, the refining the initial rule until the initial rule satisfies a preset condition includes:
and stopping refining the initial rule when the rule back part obtained according to the conjunction items added in the rule front part cannot meet the preset condition.
Specifically, the quality of the rule is improved by adding a new conjunction item on the left side of the initial rule and refining the initial rule, and the conjunction item is continuously added on the left side of the initial rule until the rule back-piece meets a preset condition, which is that in an exemplary embodiment, the added conjunction item cannot continuously improve the quality of the rule.
In an exemplary embodiment, the quality of the rule is evaluated by the accuracy and the coverage rate, that is, when the accuracy and the coverage rate of the rule are kept unchanged by adding the orientation, the rule is indicated to have satisfied the preset condition.
Wherein, the precision formula is as follows: p is TP/(TP + FP), which indicates that all the types correctly predicted are positive, and in the present embodiment, indicates that all the types correctly determined by the rules are positive, for example, 10 types of transactions whose types are high risk are determined by the rules, and 8 types of transactions are high risk, the accuracy of the rule is 80%.
The coverage formula is: recall is TP/(TP + FN); it indicates that the correct prediction TP is the proportion of all positive samples FN, in this embodiment, indicates that the correctly determined category is the proportion of all positive samples FN, for example, 10 transactions of all high-risk categories are in total, and 8 transactions of high-risk category are determined by the rule, and the coverage rate of the rule is 80%.
Wherein, TP is that the transaction is actually the category, and the rule prediction result is also the category, for example, a certain transaction is a high risk, and what is predicted by the rule is also a high risk; FP means that the transaction is not actually in that category, but is predicted to be in that category by the rules, e.g., a transaction is low or medium risk, and a transaction is predicted to be high risk by the rules; FN refers to the category that the transaction is actually in, and is predicted not to be in by the rules, e.g., the transaction is actually high risk, and low or medium risk predicted by the rules.
Step S402A, iterating the initial rule satisfying the preset condition to obtain a final rule.
Specifically, one rule includes at least one conjunction, and in the conjunction, one transaction attribute index may have a plurality of value pairs, for example, the transaction attribute index is "suspected fraud rate", the corresponding value pair may be any number between 1% and 100%, such as 10% and 15%, and because there are a plurality of categories, for example, when the transaction attribute index is suspected fraud rate, when the value pair range is "value pair ≧ 80%" is high risk, the value pair range is "value pair ≦ 50%" is medium risk, and when the value pair range is "value pair ≦ 50%" is low risk, and when one rule includes a plurality of conjunctions, two rules having the same transaction attribute index may be generated, but the optimal rule and the suboptimal rule of the value pair corresponding to the transaction attribute index may not be the same, and therefore, after the initial rule satisfies the preset condition, iteration is performed by changing the value pair corresponding to the transaction attribute index in the rule, to obtain the optimal rule.
In another embodiment, a rule that can correctly predict a category is randomly determined as an initial rule, a rule front piece of the initial rule includes M conjuncts, where M is an integer greater than 1; referring to fig. 4, step S400 may further include:
step S401B, deleting conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition;
specifically, the initial rule is a rule that can correctly predict the category but has a small range, for example, r2 ≧ 10000 ≧ 100000 ≧ 80% fraud rate ≧ high risk, i.e., high-risk transaction indicating that the transaction subject has a violation penalty of 10000 or more and a default principal of 100000 or more and a fraud rate of 80% or more, but in daily operations, it is possible to determine whether the transaction is high-risk by determining the violation penalty and the default principal, and some high-risk transactions may be missed if the fraud rate is compromised.
In an exemplary embodiment, the refining the initial rule until the initial rule satisfies a preset condition includes:
the preset condition is that the rule back-piece starts to cover a counter-example, and the counter-example is a category which cannot be determined by the rule front-piece of the initial rule.
Specifically, the quality of the rule is improved by deleting the conjuncts on the left side of the initial rule and refining the initial rule, and the conjuncts are continuously deleted on the left side of the initial rule until the rule meets a preset condition, in an exemplary embodiment, the preset condition is that the rule starts to cover the counter example. Taking the rule r2 as an example, when the conjunct item "fraud rate ≧ 80%" is deleted, the rule can still determine the high-risk transaction, but when the conjunct item "default principal fee ≧ 100000" is continuously deleted, the transaction is determined only by the "overdue penalty ≧ 10000", and some low-risk and medium-risk transactions may be misjudged as high-risk, that is, the rule starts to cover the counter example.
Step S402B, iterating the initial rule satisfying the preset condition to obtain a final rule.
Similarly, one rule includes at least one conjunction item, and in the conjunction item, one transaction attribute index may have a plurality of value pairs, and two rules with the same transaction attribute index may be generated, but the value pair corresponding to the transaction attribute index has different optimal rules and suboptimal rules, so that after the initial rule meets the preset condition, the value pair corresponding to the transaction attribute index in the rule is changed to perform iteration to obtain the optimal rule.
Step S500, extracting a plurality of key evaluation fields from the final rule, and filling the plurality of key evaluation fields into a preset transaction risk evaluation template to generate a transaction risk evaluation policy.
Specifically, by extracting key evaluation fields in different final rules and applying a key risk evaluation template, a transaction risk evaluation strategy corresponding to the final rules can be dynamically generated. And displaying the optimal rule and the corresponding evaluation result on an interface for a developer to perform rule combination on the selected final rule to obtain a transaction risk strategy.
By setting the transaction risk assessment template, the transaction risk assessment strategy is managed and controlled uniformly.
And step S600, evaluating the transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
In an exemplary embodiment, referring to fig. 5, step 600 may further include:
step S601, acquiring transaction flow data of a transaction event;
step S602, performing logic calculation on the transaction flow data according to a preset rule to obtain derivative transaction flow data;
step S603, evaluating the derived trading flow data according to the trading risk evaluation policy to obtain a risk evaluation result of the trading event.
Specifically, when risk assessment is to be performed on real-time transaction, real-time transaction flow data is obtained, logic budget is performed on the real-time transaction flow data according to a preset rule to obtain real-time derivative transaction flow data, and then the real-time derivative transaction flow data is assessed according to a risk transaction assessment side strategy to obtain risk assessment of the real-time transaction.
The invention obtains historical transaction flow data; analyzing the historical transaction flow data to obtain transaction attribute indexes corresponding to the historical transaction flow data, index data corresponding to the transaction attribute indexes and categories corresponding to the index data; generating an initial rule based on the transaction attribute index, the index data corresponding to the transaction attribute index and the category corresponding to the index data, and refining the initial rule to obtain a final rule; generating a transaction risk evaluation strategy according to the final rule; and evaluating the real-time transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event, so that the efficiency and the accuracy of transaction risk evaluation are improved.
Example two
With continued reference to FIG. 6, a schematic diagram of program modules of the transaction event risk assessment system of the present invention is shown. In this embodiment, the transaction event risk assessment system 20 may include or be divided into one or more program modules, which are stored in a storage medium and executed by one or more processors to implement the present invention and implement the transaction event risk assessment method described above. The program modules referred to in the embodiments of the present invention refer to a series of computer program instruction segments capable of performing specific functions, and are more suitable than the program itself for describing the execution process of the transaction event risk assessment system 20 in the storage medium. The following description will specifically describe the functions of the program modules of the present embodiment:
and the data acquisition module 200 is used for acquiring historical transaction flow data.
Specifically, the historical transaction flow data refers to data generated by a user during a transaction process, such as a transaction date, a transaction time, a transaction card number, a transaction account number, a region number, a website number, a location, a terminal number, a teller number, a transaction certificate, a transaction channel, and the like.
In an exemplary embodiment, historical transaction flow data is obtained via sql (structured query language) from business databases including, but not limited to: a relational database, a distributed search engine database, and a cache database. The historical transaction flow data refers to business data generated based on a business layer.
The data processing module 202 is configured to analyze the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index, and a category corresponding to the index data.
Further, the data processing module 202 is further configured to:
and performing logic calculation on the historical transaction flow data according to a preset rule to obtain historical derivative transaction flow data.
The derived transaction flow data refers to data derived by performing secondary calculation by using a preset rule based on the historical transaction flow data, for example: the loan application number is historical transaction flow data, and the average loan application number is derivative transaction flow data.
In detail, the logic calculation of the historical transaction flow data according to the preset rule to obtain derivative transaction flow data includes:
and inputting the historical transaction flow data into a preset calculation formula to obtain the derivative transaction flow data.
And the preset calculation formula can be selected and set by a developer in a self-defined way according to the requirement of the generation rule. For example: the historical transaction running data is the number of loan application strokes, the derivative transaction running data is the average number of loan application strokes per month, and the derivative running data of the number of loan application strokes per month can be obtained for n/12 through a calculation formula, wherein n is the number of loan application strokes per year.
And carrying out attribute classification on the historical derived transaction flow data to obtain a transaction attribute index and index data corresponding to the transaction attribute index.
Specifically, the index data is data used for classifying the historical derived transaction flow data, and the index data is determined according to the attribute of the historical derived transaction flow. For example, the index data may be obtained by dividing the determined index data into an average number of loan applications per month of 3-5, 3-10, 10 or more, based on the average number of loan applications per month.
And dividing the historical derived transaction flow data into corresponding categories according to the transaction attribute indexes and the index data.
Specifically, when the index data is determined to be 3-5, 3-10, 10 or more, the derivative transaction chronological data is correspondingly divided into "low risk", "medium risk", and "high risk" according to the index data, for example, taking the index data as the average number of loan applications per month as an example, when the derivative transaction chronological data is the average number of loan applications per month as 3, the category of the derivative transaction chronological data is determined to be low risk.
A rule generating module 204, configured to generate an initial rule based on the transaction attribute index, the index data corresponding to the transaction attribute index, and the category corresponding to the index data, where the initial rule includes a rule front part and a rule back part, the rule front part is a set formed by N conjunctions formed by the transaction attribute index and the index data corresponding to the transaction attribute index, and N is an integer greater than or equal to 0; the rule back-part is the category determined by the conjuncts.
In an exemplary embodiment, the rules may be expressed in the form:
ri (condition i) → yi;
the left side ri of the rule (condition i) is the rule antecedent or precondition. ri is the conjunction of the transaction attribute metrics, i.e., all transaction attribute metrics in the rule (condition i) are satisfied simultaneously.
The condition i ═ a1 op v1 ^ (a2 op v2) ^ … ^ (Aj op vj);
wherein (Aj, vj) is a transaction attribute index-value pair, the value pair is a value corresponding to the transaction attribute index, for example, the transaction attribute index is "suspected fraud rate", the value pair is 10%, op is a comparison operator, and is selected from the set { ═ not, <, > larger, ≦ and ≧ represents a parallel relationship. Each transaction attribute index-value pair (ajop vj) is referred to as a conjunction. The rule right is called the rule back-piece and contains the prediction class yi. For example, a rule r1 ≧ 10000 ≧ 100000 ≧ high risk, and a rule indicating that the overdue penalty of the transaction body is 10000 or more and the default principal is 100000 or more determines that the transaction is a high risk transaction.
The rule generating module 204 is further configured to refine the initial rule to obtain a final rule.
In an exemplary embodiment, assume that the rule antecedent of the generated initial rule is an empty set with a number of conjuncts of 0; and refining the initial rule to obtain a final rule.
Further, the rule generating module 204 is further configured to:
when the rule front piece of the initial rule is an empty set with the number of conjuncts being 0; adding conjuncts in the rule front piece one by one, and refining the initial rule until the initial rule meets a preset condition.
Specifically, the initial rule with the rule front-part conjunctive item number of 0 is as follows: r { } → y, where the left side of the rule is an empty set and the right side of the rule contains the target class. The initial rule is of poor quality because it covers all classes because it is an empty set to the right.
In an exemplary embodiment, the refining the initial rule until the initial rule satisfies a preset condition includes:
and stopping refining the initial rule when the rule back part obtained according to the conjunction items added in the rule front part cannot meet the preset condition.
Specifically, the quality of the rule is improved by adding a new conjunction item on the left side of the initial rule and refining the initial rule, and the conjunction item is continuously added on the left side of the initial rule until the rule back-piece meets a preset condition, which is that in an exemplary embodiment, the added conjunction item cannot continuously improve the quality of the rule.
In an exemplary embodiment, the quality of the rule is evaluated by the accuracy and the coverage rate, that is, when the accuracy and the coverage rate of the rule are kept unchanged by adding the orientation, the rule is indicated to have satisfied the preset condition.
Wherein, the precision formula is as follows: p is TP/(TP + FP), which indicates that all the types correctly predicted are positive, and in the present embodiment, indicates that all the types correctly determined by the rules are positive, for example, 10 types of transactions whose types are high risk are determined by the rules, and 8 types of transactions are high risk, the accuracy of the rule is 80%.
The coverage formula is: recall is TP/(TP + FN); it indicates that the correct prediction TP is the proportion of all positive samples FN, in this embodiment, indicates that the correctly determined category is the proportion of all positive samples FN, for example, 10 transactions of all high-risk categories are in total, and 8 transactions of high-risk category are determined by the rule, and the coverage rate of the rule is 80%.
Wherein, TP is that the transaction is actually the category, and the rule prediction result is also the category, for example, a certain transaction is a high risk, and what is predicted by the rule is also a high risk; FP means that the transaction is not actually in that category, but is predicted to be in that category by the rules, e.g., a transaction is low or medium risk, and a transaction is predicted to be high risk by the rules; FN refers to the category that the transaction is actually in, and is predicted not to be in by the rules, e.g., the transaction is actually high risk, and low or medium risk predicted by the rules.
And iterating the initial rules meeting the preset conditions to obtain final rules.
Specifically, one rule includes at least one conjunction, and in the conjunction, one transaction attribute index may have a plurality of value pairs, for example, the transaction attribute index is "suspected fraud rate", the corresponding value pair may be any number between 1% and 100%, such as 10% and 15%, and because there are a plurality of categories, for example, when the transaction attribute index is suspected fraud rate, when the value pair range is "value pair ≧ 80%" is high risk, the value pair range is "value pair ≦ 50%" is medium risk, and when the value pair range is "value pair ≦ 50%" is low risk, and when one rule includes a plurality of conjunctions, two rules having the same transaction attribute index may be generated, but the optimal rule and the suboptimal rule of the value pair corresponding to the transaction attribute index may not be the same, and therefore, after the initial rule satisfies the preset condition, iteration is performed by changing the value pair corresponding to the transaction attribute index in the rule, to obtain the optimal rule.
And iterating the initial rules meeting the preset conditions to obtain final rules.
Randomly determining a rule which can correctly predict a category as an initial rule, wherein a rule front piece of the initial rule comprises M conjuncts, and M is an integer greater than 1.
Further, the rule generating module 204 is further configured to:
deleting conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition;
and iterating the initial rules meeting the preset conditions to obtain final rules.
Similarly, one rule includes at least one conjunction item, and in the conjunction item, one transaction attribute index may have a plurality of value pairs, and two rules with the same transaction attribute index may be generated, but the value pair corresponding to the transaction attribute index has different optimal rules and suboptimal rules, so that after the initial rule meets the preset condition, the value pair corresponding to the transaction attribute index in the rule is changed to perform iteration to obtain the optimal rule.
And a policy generation module 206, configured to extract a plurality of key evaluation fields from the final rule, and fill the plurality of key evaluation fields in a preset transaction risk evaluation template, so as to generate a transaction risk evaluation policy.
Specifically, by extracting key evaluation fields in different final rules and applying a key risk evaluation template, a transaction risk evaluation strategy corresponding to the final rules can be dynamically generated. And displaying the optimal rule and the corresponding evaluation result on an interface for a developer to perform rule combination on the selected final rule to obtain a transaction risk strategy.
By setting the transaction risk assessment template, the transaction risk assessment strategy is managed and controlled uniformly.
And the evaluation module 208 is configured to evaluate the transaction event according to the transaction risk evaluation policy to obtain a risk evaluation result of the transaction event.
Further, the evaluation module 208 is further configured to: .
Acquiring transaction flow data of a transaction event;
performing logic calculation on the transaction flow data according to a preset rule to obtain derivative transaction flow data;
and evaluating the derived transaction running data according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
Specifically, when risk assessment is to be performed on real-time transaction, real-time transaction flow data is obtained, logic budget is performed on the real-time transaction flow data according to a preset rule to obtain real-time derivative transaction flow data, and then the real-time derivative transaction flow data is assessed according to a risk transaction assessment side strategy to obtain risk assessment of the real-time transaction.
EXAMPLE III
Fig. 7 is a schematic diagram of a hardware architecture of a computer device according to a third embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown in FIG. 7, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a transaction event risk assessment system 20, which may be communicatively coupled to each other via a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used for storing an operating system and various application software installed on the computer device 2, such as the program codes of the transaction event risk assessment system 20 of the second embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 2. In this embodiment, the processor 22 is configured to run the program codes stored in the memory 21 or process data, for example, run the transaction event risk assessment system 20, so as to implement the transaction event risk assessment method of the above embodiment.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 7 only shows the computer device 2 with components 20-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the transaction event risk assessment system 20 stored in the memory 21 may be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
For example, fig. 6 shows a schematic diagram of program modules of the second embodiment for implementing the transaction event risk assessment system 20, in this embodiment, the transaction event risk assessment system 20 may be divided into a data acquisition module 200, a data processing module 202, a rule generation module 204, a policy generation module 206, and an assessment module 208. The program modules referred to herein are a series of computer program instruction segments that can perform specific functions, and are more suitable than programs for describing the execution of the transaction event risk assessment system 20 on the computer device 2. The specific functions of the program module data obtaining module 200-the evaluating module 208 have been described in detail in the second embodiment, and are not described herein again.
Example four
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of the present embodiment is used for storing the transaction event risk assessment system 20, and when being executed by a processor, the transaction event risk assessment method of the first embodiment is implemented.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (10)

1. A transaction event risk assessment method, comprising:
acquiring historical transaction flow data;
analyzing the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index and a category corresponding to the index data;
generating an initial rule based on the transaction attribute index, index data corresponding to the transaction attribute index and a category corresponding to the index data, wherein the initial rule comprises a rule front piece and a rule back piece, the rule front piece is a set formed by N conjuncts formed by the transaction attribute index and the index data corresponding to the transaction attribute index, and N is an integer greater than or equal to 0; the rule back part is a category determined by the conjuncts;
refining the initial rule to obtain a final rule;
extracting a plurality of key evaluation fields from the final rule, and filling the key evaluation fields into a preset transaction risk evaluation template to generate a transaction risk evaluation strategy;
and evaluating the transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
2. The transaction event risk assessment method according to claim 1, wherein the analyzing the historical transaction flow data to obtain the transaction attribute index corresponding to the historical transaction flow data, the index data corresponding to the transaction attribute index, and the category corresponding to the index data comprises:
performing logic calculation on the historical transaction flow data according to a preset rule to obtain historical derivative transaction flow data;
performing attribute classification on the historical derived transaction flow data to obtain transaction attribute indexes and index data corresponding to the transaction attribute indexes;
and dividing the historical derived transaction running data according to the transaction attribute indexes and the index data to obtain categories corresponding to the index data.
3. The transaction event risk assessment method according to claim 2, wherein the rule antecedents of the initial rule are empty sets with a number of conjuncts of 0; the refinement of the initial rule to obtain a final rule comprises:
adding conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition;
and iterating the initial rules meeting the preset conditions to obtain final rules.
4. The transaction event risk assessment method according to claim 3, wherein the refining the initial rule until the initial rule satisfies a preset condition comprises:
and stopping refining the initial rule when the rule back part obtained according to the conjunction items added in the rule front part cannot meet the preset condition.
5. The transaction event risk assessment method according to claim 2, wherein a rule that can correctly predict the category is randomly determined as an initial rule, and a rule antecedent of the initial rule includes M conjunctions, where M is an integer greater than 1; the refinement of the initial rule to obtain a final rule comprises:
deleting conjuncts in the rule antecedents one by one, and refining the initial rule until the initial rule meets a preset condition;
and iterating the initial rules meeting the preset conditions to obtain final rules.
6. The transaction event risk assessment method according to claim 5, wherein the refining the initial rule until the initial rule satisfies a preset condition comprises:
the preset condition is that the rule back-piece starts to cover a counter-example, and the counter-example is a category which cannot be determined by the rule front-piece of the initial rule.
7. The transaction event risk assessment method according to claim 1, wherein the assessing the transaction event according to the transaction risk assessment policy to obtain the risk assessment result of the transaction event comprises:
acquiring transaction flow data of a transaction event;
performing logic calculation on the transaction flow data according to a preset rule to obtain derivative transaction flow data;
and evaluating the derived transaction running data according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
8. A transaction event risk assessment system, comprising:
the data acquisition module is used for acquiring historical transaction flow data;
the data processing module is used for analyzing the historical transaction flow data to obtain a transaction attribute index corresponding to the historical transaction flow data, index data corresponding to the transaction attribute index and a category corresponding to the index data;
a rule generating module, configured to generate an initial rule based on the transaction attribute index, the index data corresponding to the transaction attribute index, and the category corresponding to the index data, where the initial rule includes a rule front part and a rule back part, the rule front part is a set formed by N conjunctions formed by the transaction attribute index and the index data corresponding to the transaction attribute index, and N is an integer greater than or equal to 0; the rule back part is a category determined by the conjuncts;
the rule generating module is further configured to refine the initial rule to obtain a final rule;
the strategy generation module is used for extracting a plurality of key evaluation fields from the final rule and filling the key evaluation fields into a preset transaction risk evaluation template so as to generate a transaction risk evaluation strategy;
and the evaluation module is used for evaluating the transaction event according to the transaction risk evaluation strategy to obtain a risk evaluation result of the transaction event.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the transaction event risk assessment method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having stored therein a computer program executable by at least one processor to cause the at least one processor to perform the steps of the transaction event risk assessment method according to any one of claims 1 to 7.
CN202011537443.6A 2020-12-23 2020-12-23 Transaction risk assessment method, system, device and storage medium Pending CN112598422A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011537443.6A CN112598422A (en) 2020-12-23 2020-12-23 Transaction risk assessment method, system, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011537443.6A CN112598422A (en) 2020-12-23 2020-12-23 Transaction risk assessment method, system, device and storage medium

Publications (1)

Publication Number Publication Date
CN112598422A true CN112598422A (en) 2021-04-02

Family

ID=75200844

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011537443.6A Pending CN112598422A (en) 2020-12-23 2020-12-23 Transaction risk assessment method, system, device and storage medium

Country Status (1)

Country Link
CN (1) CN112598422A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050283751A1 (en) * 2004-06-18 2005-12-22 International Business Machines Corporation Method and apparatus for automated risk assessment in software projects
US20160104163A1 (en) * 2014-10-14 2016-04-14 Jpmorgan Chase Bank, N.A. ldentifying Potentially Risky Transactions
CN106779755A (en) * 2016-12-31 2017-05-31 湖南文沥征信数据服务有限公司 A kind of network electric business borrows or lends money methods of risk assessment and model

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050283751A1 (en) * 2004-06-18 2005-12-22 International Business Machines Corporation Method and apparatus for automated risk assessment in software projects
US20160104163A1 (en) * 2014-10-14 2016-04-14 Jpmorgan Chase Bank, N.A. ldentifying Potentially Risky Transactions
CN106779755A (en) * 2016-12-31 2017-05-31 湖南文沥征信数据服务有限公司 A kind of network electric business borrows or lends money methods of risk assessment and model

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ANDYZENG24: "数据挖掘之分类——基于规则的分类器", pages 1 - 3, Retrieved from the Internet <URL:https://www.cnblogs.com/zengzhihua/p/5458373.html> *

Similar Documents

Publication Publication Date Title
CN107679995B (en) Electronic device, insurance case claim settlement auditing method and computer-readable storage medium
US20120278217A1 (en) Systems and methods for improving prediction of future credit risk performances
CN107622326B (en) User classification and available resource prediction method, device and equipment
CN112100219A (en) Report generation method, device, equipment and medium based on database query processing
CN111709826A (en) Target information determination method and device
CN111798301A (en) Resource transfer quota determining method, device and system
JP2016099915A (en) Server for credit examination, system for credit examination, and program for credit examination
CN111524015A (en) Method and device for training prediction model, computer equipment and readable storage medium
CN111798246A (en) Financial risk grade assessment method and device
CN111242779B (en) Financial data characteristic selection and prediction method, device, equipment and storage medium
CN112651632A (en) Information analysis processing method and device based on marketing data
CN110544165A (en) credit risk score card creating method and device and electronic equipment
CN115759742A (en) Enterprise risk assessment method and device, computer equipment and storage medium
CN112598422A (en) Transaction risk assessment method, system, device and storage medium
CN115936875A (en) Financial product form hanging processing method and device
CN116150200A (en) Data processing method, device, electronic equipment and storage medium
US10235719B2 (en) Centralized GAAP approach for multidimensional accounting to reduce data volume and data reconciliation processing costs
CN114925275A (en) Product recommendation method and device, computer equipment and storage medium
US20220156666A1 (en) Systems and methods for confidence interval transaction settlement range predictions
CN114638503A (en) Asset risk pressure testing method, device, equipment and storage medium
CN114154712A (en) Data management method, data management device, equipment and storage medium
CN113849618A (en) Strategy determination method and device based on knowledge graph, electronic equipment and medium
CN114548463A (en) Line information prediction method, line information prediction device, computer equipment and storage medium
CN113240472B (en) Financial product recommendation method, electronic equipment and storage medium
JP5592861B2 (en) Claim evaluation support system, claim evaluation support method and claim evaluation support program

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