CN112214529A - Financial object abnormal factor priority analysis method based on multi-objective optimization - Google Patents

Abstract

The invention discloses a financial object abnormal factor priority analysis method based on multi-objective optimization, which comprises the following steps: s1, calculating the transaction failure rate and the failure contribution degree of each abnormal factor for a target financial object with known abnormal factors; s2, taking the abnormal factors of the target financial object as multi-objective optimization solutions, and determining the domination relationship among the solutions according to the transaction failure rate and the failure contribution degree of each abnormal factor; s3, for each solution, counting the number of dominant solutions of the solution according to the determined dominant relationship; and S4, sequencing the solutions from small to large according to the number of dominant solutions, wherein the less the number of dominant solutions, the higher the priority. The invention can obtain effective abnormal factor priority ordering, thereby providing a basis for rapidly positioning the reason of transaction failure.

Description

Financial object abnormal factor priority analysis method based on multi-objective optimization

Technical Field

The invention relates to financial data analysis, in particular to a financial object abnormal factor priority analysis method based on multi-objective optimization.

Background

In the current society, mobile payment is the mainstream, and how to submit transaction success rate and enhance user experience is a problem that payment enterprises and related merchants and banking institutions need to pay attention to. Payment is a long-link transaction activity with numerous participants, including: the factors causing transaction failure of a cardholder or a payment user, a merchant, an acquirer, an issuer, an internet or a bank union and other related mechanisms may be single factors, but more factors are combined or overlapped, and many failure factors cannot be judged by one point. In addition, the success rate of the current transaction is very high, the overall transaction success rate is generally about 99%, and it is very difficult to find and find the problem and reason of the transaction failure in the face of massive payment transaction data.

Generally, some abnormal factors of the financial object can be obtained through preliminary data analysis, but it is difficult to know which one or more of the abnormal factors causes higher probability of transaction failure, which is not beneficial to quickly locate the reason causing the transaction failure.

Disclosure of Invention

The invention aims to overcome the defects of the prior art and provides a financial object abnormal factor priority analysis method based on multi-objective optimization, which can obtain effective abnormal factor priority sequencing and further provide a basis for quickly positioning the reason of transaction failure.

The purpose of the invention is realized by the following technical scheme: a financial object abnormal factor priority analysis method based on multi-objective optimization comprises the following steps:

s1, calculating the transaction failure rate and the failure contribution degree of each abnormal factor for a target financial object with known abnormal factors;

s2, taking the abnormal factors of the target financial object as multi-objective optimization solutions, and determining the domination relationship among the solutions according to the transaction failure rate and the failure contribution degree of each abnormal factor;

s3, for each solution, counting the number of dominant solutions of the solution according to the determined dominant relationship;

and S4, sequencing the solutions from small to large according to the number of dominant solutions, wherein the less the number of dominant solutions, the higher the priority.

The step S1 includes:

s101, giving a plurality of factors influencing the quality of financial transaction data, and dividing the factors into four aspects of a card, a communication route, an operation and a terminal, wherein: card-wise factors include: card BIN, card properties, and card media; factors in the communication route include: accepting the organization identification code, the card issuing organization identification code, the sending organization identification code and the receiving organization identification code; operational factors include: transaction codes, service point input modes and service point condition codes; factors on the part of the terminal include: merchant type, transaction channel, card receiving and issuing merchant identification code;

the method comprises the following steps of taking a plurality of objects under an acceptance organization identification code as financial objects, and taking other factors except the acceptance organization identification code as factors of each financial object; setting an abnormal factor of a known target financial object for the target financial object;

s102, acquiring financial transaction data within a certain time, dividing the financial transaction data under each financial object, and dividing the financial transaction data under each financial object according to factors to obtain the financial transaction data of each factor under each financial object;

s103, counting the total number of the financial transaction data failed by all the financial objects, the number of the financial transaction data under the target financial object and the number of the financial transaction data failed by each abnormal factor of the target financial object;

s104, calculating the transaction failure rate ER of the jth abnormal factor under the target financial object_ijAnd degree of failure contribution EC_ij：

Wherein i represents that the target financial object is the ith financial object under the identification code of the acceptance organization, the value of i is an integer which is not less than 1 and not more than the total number of the financial objects,

representing the number of financial transaction data failed by the jth anomalous factor of the target financial object, N_iRepresenting the amount of financial transaction data under the target financial object, N^EPresentation instrumentA total number of financial transaction data for which the financial object failed;

s105, when j is 1, 2.. times, k, repeating step S104 to obtain a transaction failure rate and a failure contribution degree of each abnormal factor under the target financial object; where k is the number of abnormal factors under the target financial object, and k is an integer of not less than 1 and not more than 12.

The step S2 includes:

s201, taking abnormal factors of the target financial object as a solution of multi-objective optimization;

s202, determining a dominance relation among solutions:

for any two solutions, any two solutions x⁽¹⁾、x⁽²⁾There are two cases:

first, when | f_m(x⁽¹⁾)-f_m(x⁽²⁾) If two conditions of (1) and (2) are simultaneously satisfied when l > d, then x⁽¹⁾Dominating x⁽²⁾I.e. x⁽¹⁾Is x⁽²⁾If (1) and (2) cannot be simultaneously satisfied, then x⁽¹⁾Does not dominate x⁽²⁾；

(1) When m takes an arbitrary value in the set {1,2}, x⁽¹⁾Is an objective function f_mx⁽¹⁾Are all no better than x⁽²⁾Is an objective function f_mx⁽²⁾The difference, i.e., for any m e {1,2 }:

f_m(x⁽¹⁾)≤f_m(x⁽²⁾)；

(2) at least one m e {1,2} exists such that x⁽¹⁾Ratio x⁽²⁾Strictly preferred, i.e. there is at least one m such that:

f_m(x⁽¹⁾)＜f_m(x⁽²⁾)；

second, when | f_m(x⁽¹⁾)-f_m(x⁽²⁾) When | ≦ d, consider x⁽¹⁾And x⁽²⁾Are undifferentiated, and do not mutually dominate each other;

wherein, when m is 1, f_mx⁽¹⁾、f_mx⁽²⁾Denotes x⁽¹⁾、x⁽²⁾F when m is 2_mx⁽¹⁾、f_mx⁽²⁾Denotes x⁽¹⁾、x⁽²⁾The degree of the failure contribution.

In step S4, the higher the priority of the solution is, the higher the probability that the transaction will fail due to the abnormal factor corresponding to the solution is considered to be.

The invention has the beneficial effects that: the effective abnormal factor priority ranking can be obtained, so that the probability of transaction failure caused by which one or more abnormal factors is/are higher is obtained, and a basis is provided for quickly positioning the reason of the transaction failure.

Drawings

FIG. 1 is a flow chart of the method of the present invention.

Detailed Description

The technical solutions of the present invention are further described in detail below with reference to the accompanying drawings, but the scope of the present invention is not limited to the following.

As shown in fig. 1, a method for analyzing the priority of abnormal factors of financial objects based on multi-objective optimization includes the following steps:

s1, calculating the transaction failure rate and the failure contribution degree of each abnormal factor for a target financial object with known abnormal factors;

s2, taking the abnormal factors of the target financial object as multi-objective optimization solutions, and determining the domination relationship among the solutions according to the transaction failure rate and the failure contribution degree of each abnormal factor;

s3, for each solution, counting the number of dominant solutions of the solution according to the determined dominant relationship;

and S4, sequencing the solutions from small to large according to the number of dominant solutions, wherein the less the number of dominant solutions, the higher the priority.

In an embodiment of the present application, the step S1 includes:

s101, given a plurality of factors influencing the quality of financial transaction data, the given factors are divided into four aspects of a card, a communication route, an operation and a terminal in the embodiment of the application to provide 13 factors, wherein: card-wise factors include: card BIN, card properties, and card media; factors in the communication route include: accepting the organization identification code, the card issuing organization identification code, the sending organization identification code and the receiving organization identification code; operational factors include: transaction codes, service point input modes and service point condition codes; factors on the part of the terminal include: merchant type, transaction channel, card receiving and issuing merchant identification code;

the method comprises the following steps of taking a plurality of objects under an acceptance organization identification code as financial objects (because different acceptance organization identification codes correspond to different acceptance organizations, the objects under the acceptance organization identification code are actually all the acceptance organizations), and taking the rest 12 factors except the acceptance organization identification code as the factors of each financial object; setting an abnormal factor of a known target financial object for the target financial object;

s102, acquiring financial transaction data within a certain time, dividing the financial transaction data under each financial object, and dividing the financial transaction data under each financial object according to factors to obtain the financial transaction data of each factor under each financial object;

s103, counting the total number of the financial transaction data failed by all the financial objects, the number of the financial transaction data under the target financial object and the number of the financial transaction data failed by each abnormal factor of the target financial object;

s104, calculating the transaction failure rate ER of the jth abnormal factor under the target financial object_ijAnd degree of failure contribution EC_ij：

Wherein i represents that the target financial object is the ith financial object under the identification code of the acceptance organization, the value of i is an integer which is not less than 1 and not more than the total number of the financial objects,

the j-th abnormal factor of the target financial objectNumber of financial transaction data failed, N_iRepresenting the amount of financial transaction data under the target financial object, N^EA total number of financial transaction data representing all financial objects that failed;

s105, when j is 1, 2.. times, k, repeating step S104 to obtain a transaction failure rate and a failure contribution degree of each abnormal factor under the target financial object; where k is the number of abnormal factors under the target financial object, and k is an integer of not less than 1 and not more than 12.

Further, the step S2 includes:

s201, taking abnormal factors of the target financial object as a solution of multi-objective optimization;

s202, determining a dominance relation among solutions:

for any two solutions, any two solutions x⁽¹⁾、x⁽²⁾There are two cases:

first, when | f_m(x⁽¹⁾)-f_m(x⁽²⁾) If two conditions of (1) and (2) are simultaneously satisfied when l > d, then x⁽¹⁾Dominating x⁽²⁾I.e. x⁽¹⁾Is x⁽²⁾If (1) and (2) cannot be simultaneously satisfied, then x⁽¹⁾Does not dominate x⁽²⁾；

(1) When m takes an arbitrary value in the set {1,2}, x⁽¹⁾Is an objective function f_mx⁽¹⁾Are all no better than x⁽²⁾Is an objective function f_mx⁽²⁾The difference, i.e., for any m e {1,2 }:

f_m(x⁽¹⁾)≤f_m(x⁽²⁾)；

(2) at least one m e {1,2} exists such that x⁽¹⁾Ratio x⁽²⁾Strictly preferred, i.e. there is at least one m such that:

f_m(x⁽¹⁾)＜f_m(x⁽²⁾)；

second, when | f_m(x⁽¹⁾)-f_m(x⁽²⁾) When | ≦ d, consider x⁽¹⁾And x⁽²⁾Are undifferentiated, and do not mutually dominate each other;

wherein, when m is 1, f_mx⁽¹⁾、f_mx⁽²⁾Denotes x⁽¹⁾、x⁽²⁾F when m is 2_mx⁽¹⁾、f_mx⁽²⁾Denotes x⁽¹⁾、x⁽²⁾The degree of the failure contribution.

In step S4, the higher the priority of the solution is, the higher the probability that the transaction will fail due to the abnormal factor corresponding to the solution is considered to be.

Through the priority ranking obtained by the method, the probability that which one or more abnormal factors cause transaction failure is higher can be obtained, a basis is provided for quickly positioning the reason of the transaction failure, and convenience is provided for the analysis of financial transaction data.

The foregoing is a preferred embodiment of the present invention, it is to be understood that the invention is not limited to the form disclosed herein, but is not to be construed as excluding other embodiments, and is capable of other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (4)

1. A financial object abnormal factor priority analysis method based on multi-objective optimization is characterized by comprising the following steps: the method comprises the following steps:

s1, calculating the transaction failure rate and the failure contribution degree of each abnormal factor for a target financial object with known abnormal factors;

s2, taking the abnormal factors of the target financial object as multi-objective optimization solutions, and determining the domination relationship among the solutions according to the transaction failure rate and the failure contribution degree of each abnormal factor;

s3, for each solution, counting the number of dominant solutions of the solution according to the determined dominant relationship;

and S4, sequencing the solutions from small to large according to the number of dominant solutions, wherein the less the number of dominant solutions, the higher the priority.

2. The method of claim 1, wherein the method comprises: the step S1 includes:

s101, giving a plurality of factors influencing the quality of financial transaction data, and dividing the factors into four aspects of a card, a communication route, an operation and a terminal, wherein: card-wise factors include: card BIN, card properties, and card media; factors in the communication route include: accepting the organization identification code, the card issuing organization identification code, the sending organization identification code and the receiving organization identification code; operational factors include: transaction codes, service point input modes and service point condition codes; factors on the part of the terminal include: merchant type, transaction channel, card receiving and issuing merchant identification code;

the method comprises the following steps of taking a plurality of objects under an acceptance organization identification code as financial objects, and taking other factors except the acceptance organization identification code as factors of each financial object; setting an abnormal factor of a known target financial object for the target financial object;

s102, acquiring financial transaction data within a certain time, dividing the financial transaction data under each financial object, and dividing the financial transaction data under each financial object according to factors to obtain the financial transaction data of each factor under each financial object;

s103, counting the total number of the financial transaction data failed by all the financial objects, the number of the financial transaction data under the target financial object and the number of the financial transaction data failed by each abnormal factor of the target financial object;

s104, calculating the transaction failure rate ER of the jth abnormal factor under the target financial object_ijAnd degree of failure contribution EC_ij：

Wherein i represents that the target financial object is the ith financial object under the identification code of the acceptance organization, the value of i is an integer which is not less than 1 and not more than the total number of the financial objects,

representing the number of financial transaction data failed by the jth anomalous factor of the target financial object, N_iRepresenting the amount of financial transaction data under the target financial object, N^EA total number of financial transaction data representing all financial objects that failed;

s105, when j is 1, 2.. times, k, repeating step S104 to obtain a transaction failure rate and a failure contribution degree of each abnormal factor under the target financial object; where k is the number of abnormal factors under the target financial object, and k is an integer of not less than 1 and not more than 12.

3. The method of claim 1, wherein the method comprises: the step S2 includes:

s201, taking abnormal factors of the target financial object as a solution of multi-objective optimization;

s202, determining a dominance relation among solutions:

for any two solutions, any two solutions x⁽¹⁾、x⁽²⁾There are two cases:

first, when | f_m(x⁽¹⁾)-f_m(x⁽²⁾) If two conditions of (1) and (2) are simultaneously satisfied when l > d, then x⁽¹⁾Dominating x⁽²⁾I.e. x⁽¹⁾Is x⁽²⁾If (1) and (2) cannot be simultaneously satisfied, then x⁽¹⁾Does not dominate x⁽²⁾；

(1) When m takes an arbitrary value in the set {1,2}, x⁽¹⁾Is an objective function f_mx⁽¹⁾Are all no better than x⁽²⁾Is an objective function f_mx⁽²⁾The difference, i.e., for any m e {1,2 }:

f_m(x⁽¹⁾)≤f_m(x⁽²⁾)；

(2) at least one m e {1,2} exists such that x⁽¹⁾Ratio x⁽²⁾Strictly preferred, i.e. there is at least one m such that:

second, when | f_m(x⁽¹⁾)-f_m(x⁽²⁾) When | ≦ d, consider x⁽¹⁾And x⁽²⁾Are undifferentiated, and do not mutually dominate each other;

wherein, when m is 1, f_mx⁽¹⁾、f_mx⁽²⁾Denotes x⁽¹⁾、x⁽²⁾F when m is 2_mx⁽¹⁾、f_mx⁽²⁾Denotes x⁽¹⁾、x⁽²⁾The degree of the failure contribution.

4. The method of claim 1, wherein the method comprises: in step S4, the higher the priority of the solution is, the higher the probability that the transaction will fail due to the abnormal factor corresponding to the solution is considered to be.

Images