CN112465624A - Personal credit evaluation method based on social media state - Google Patents

Personal credit evaluation method based on social media state Download PDF

Info

Publication number
CN112465624A
CN112465624A CN202011202397.4A CN202011202397A CN112465624A CN 112465624 A CN112465624 A CN 112465624A CN 202011202397 A CN202011202397 A CN 202011202397A CN 112465624 A CN112465624 A CN 112465624A
Authority
CN
China
Prior art keywords
index
social
social media
hierarchical
indexes
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
CN202011202397.4A
Other languages
Chinese (zh)
Inventor
刘晓东
刘佳澄
何望君
赵阳阳
张福浩
石丽红
仇阿根
陶坤旺
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.)
Chinese Academy of Surveying and Mapping
Original Assignee
Chinese Academy of Surveying and Mapping
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 Chinese Academy of Surveying and Mapping filed Critical Chinese Academy of Surveying and Mapping
Priority to CN202011202397.4A priority Critical patent/CN112465624A/en
Publication of CN112465624A publication Critical patent/CN112465624A/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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Computing Systems (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Technology Law (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Compared with the prior art, the invention provides a social media data including WeChat, microblog and the like, defines three aspects of credit degree, rule compliance degree and financial condition and carries out dimension concretization by combining the characteristics of social media.

Description

Personal credit evaluation method based on social media state
Technical Field
The invention relates to the technical field of big data analysis, in particular to a personal credit evaluation method based on social media states.
Background
With the accelerated construction of the credit system in China and the rapid improvement of the credit consciousness of the people, the construction of the credit investigation system is particularly important. Personal credit evaluation is an important evaluation index in personal credit investigation. The development of the internet and big data technology greatly expands the connotation and extension of credit investigation, so that the related credit economy field is wider and wider, and the application of personal credit scenes based on big data is naturally diversified. Therefore, the traditional shaping mode cannot adapt to the personal credit investigation requirements under new conditions, meanwhile, a plurality of emerging big data personal credit investigation mechanisms are provided, each of the emerging big data personal credit investigation mechanisms has a unique development mode and a corresponding business field, and the quality of the provided credit products and services is greatly different, such as researching the big data credit investigation (telecommunication big data and government affair big data) from the aspects of data collection, data scenes and the like. However, the social media state data is less used for personal credit investigation, the social media data credit investigation is adopted abroad at present, particularly in the aspect of small loan, a good effect is achieved, China is actively exploring, and the problem that the personal credit investigation service scene is single in China is further enriched, so that the social media state data not only serves the economic field, but also serves the market service and the government.
By acquiring state information of a plurality of social media of a user, such as reliability, social activity, rule compliance, financial conditions and the like according to an account number, basic information related to the user, such as consumption information, personal preference, family environment, transaction history and other semi-structured behavior data, multi-dimensional credit data is enriched. Social network media accumulated a large amount of information is provided by the economic academy of Russian national research university, namely Alleksch, and is an inexhaustible information source, and social data can bring a valuable credit scoring system. The person in charge of the Tencent Credit investigation is concerned that the social media data can improve the accuracy of personal Credit investigation, and the group, the predictability and the relationship of the social network data are that the social network data can be applied to the credit investigation industry and used as the basis and the foundation for evaluating personal credit.
In general, the evaluation of the credit of a plurality of social media data such as WeChat and microblog in a social network is a powerful supplement to the evaluation of the credit in off-line life, so that the situation of inconsistent online and offline credit is avoided, and compared with the traditional credit investigation system which only evaluates economic assets independently, the state characteristic cannot be well reflected; the social media state user evaluation system can also cover scenes of job hunting, promotion and the like, and carries out prediction analysis according to the behavior of the social network to identify which aspect of the social media user is more prominent in quality; meanwhile, the credit evaluation is beneficial to the social users to monitor themselves, the integrity of the social users and the rule compliance degree are improved, the network environment is purified, and the monitoring personnel can take early warning measures for the users with low scores. The method and the device reduce the potential risks of the social network data and the unsound legal system, improve the safety of the social network data and guarantee the evaluation effectiveness of the social network data. Therefore, it is very important to adopt the social media status as a supplement to credit.
Therefore, how to supplement personal credit investigation based on various information of social media becomes a technical problem which needs to be solved urgently in the prior art.
Disclosure of Invention
The invention aims to provide a personal credit evaluation method based on a social media state, which evaluates personal credits by utilizing information acquired from social or payment software such as WeChat, microblog, Taobao, Paibao and the like, powerfully supplements evaluation for offline domestic credits, avoids the occurrence of online and offline credit inconsistency and is more objective and comprehensive for personal credit evaluation.
In order to achieve the purpose, the invention adopts the following technical scheme:
a personal credit evaluation method based on social media state is characterized by comprising the following steps:
social media status information acquisition and preprocessing step S110
Acquiring state information of the same user in a plurality of social media, wherein the state information comprises personal identity information and process information, the personal identity information comprises gender, age, education level, mobile phone number and the like, and the process information comprises information generated in the social contact, communication, entertainment, learning and payment processes of the user;
personal credit evaluation index system construction step S120
Establishing five types of hierarchical evaluation indexes by utilizing social media state information according to the influence of different social media state information on personal credit conditions, wherein each hierarchical evaluation index comprises a plurality of bottom layer indexes, and each evaluation index is assigned to obtain a scoring matrix, and the five types of hierarchical evaluation indexes are account reliability, social activity, rule adherence, network consumption preference and financial conditions respectively;
credit index weight acquisition step S130:
in the five types of hierarchical evaluation indexes, importance comparison is carried out on a plurality of bottom indexes in each hierarchical evaluation index, and the weight coefficient of each bottom index in the hierarchical evaluation indexes is determined;
final score H calculation step S140:
and multiplying the score of the bottom layer index in each hierarchical evaluation index by the weight value of the corresponding bottom layer index by using an AHP (analytic hierarchy process), and summarizing the five hierarchical evaluation indexes to obtain a final score H.
Optionally, in the social media status information obtaining and preprocessing step S110,
the method can cooperate with a plurality of social media platforms, and the state information of the same user in a plurality of social media is obtained through the identification card number, wherein the social media platforms not only comprise traditional social platforms such as WeChat, microblog and sticking bar, but also comprise shopping and payment social software such as Taobao and Paobao.
Optionally, in the social media status information obtaining and preprocessing step S110,
after the data are obtained, data preprocessing is carried out, wherein the data preprocessing comprises the steps of removing new registered accounts, carrying out data cleaning and structuring on the obtained data, and storing the data in a database.
Optionally, in the step S120 of constructing the personal credit evaluation index system, the account reliability, social activity, rule compliance, network consumption preference, and financial status are respectively specifically:
1) the account reliability hierarchical indexes comprise user age, user education degree, user working age, real name authentication, mobile phone number binding, bank card binding quantity and related transaction platform quantity;
2) the social activity level indexes comprise authenticity of information issued by a user, fluctuation conditions of the number of friends of the user and authenticity of completion of a hosting activity;
3) the rule adherence hierarchical index comprises user transmitting bad information condition, user releasing content violation times and group creating violation condition;
4) network consumption preference layering indexes comprise consumption types, group purchase participation times and concerned shops;
5) and the financial information hierarchical indexes comprise the balance of the social account, the annual income of the social account, the number of owing times of the installment repayment and the period of owing of the social account.
Optionally, the step S130 of scoring the credit indicator and obtaining the weight specifically includes:
(1) in each hierarchical index system, carrying out importance comparison on every two of a plurality of bottom layer indexes contained in the hierarchical evaluation index to obtain a judgment matrix C;
in the comparison of importance, a scale of nine decimals is usedijThe comparison result of the ith factor to the j factors is shown, 1-9 shows that the ith factor is equally important to extremely important, and 1-1/9 shows that the ith factor is equally important to extremely unimportant;
(2)for the judgment matrix C, a maximum feature root λ max and a feature vector matrix W with respect to the maximum feature root λ max in which a component W is present are obtained using the following formula (1)iIs the weight value corresponding to the bottom layer index
CW＝λmaxW(1)。
Optionally, consistency check is performed on the corresponding scoring matrix when the maximum feature root λ max is obtained.
The consistency test is as follows: and C.I is used as a consistency index and is expressed by a formula, wherein N is the order number of a C matrix, namely the number of the bottom index layers in a certain sub-index layer.
Figure BDA0002755761210000051
And obtaining a consistency index R.I, wherein the R.I can be obtained through query, calculating a consistency parameter C.R through a formula (2), if the C.R is less than or equal to 0.1, judging that the scoring matrix meets the consistency, and if the consistency is not met, adjusting the scoring matrix to reduce the subjective error of the scoring matrix until the scoring matrix is qualified.
Figure BDA0002755761210000052
Compared with the prior art, the individual credit evaluation method based on the social media state provided by the invention has the advantages that various social media data including WeChat, microblog and the like are defined in three aspects of credit degree, rule compliance degree and financial condition and are subjected to dimension concretization by combining the characteristics of social media.
Drawings
FIG. 1 is a flow diagram of a social media status based personal credit evaluation method in accordance with the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
The invention provides a method for evaluating credit of a social agent in a social network, which comprises the steps of defining multiple social media data such as WeChat and microblog in three aspects of credibility, rule compliance and financial condition, carrying out dimension concretization by combining the characteristics of social media, determining the weight of each index credit evaluation process by combining an AHP (advanced high-performance analysis) analytic hierarchy process, and multiplying specific numerical values of each index in an index evaluation table to obtain a final score H of an evaluator, so that the credit of the social agent in the social network is evaluated.
Specifically, referring to fig. 1, a flowchart of a social media status-based personal credit rating method according to the present invention is shown, including the following steps:
social media status information acquisition and preprocessing step S110
The method comprises the steps of obtaining state information of the same user in a plurality of social media, wherein the state information comprises personal identity information and process information, the personal identity information comprises gender, age, education degree, mobile phone number and the like, and the process information comprises information generated in the social contact, communication, entertainment, learning and payment processes of the user.
In an optional embodiment, the method can cooperate with a plurality of social media platforms to acquire the state information of the same user in a plurality of social media through the identification number, wherein the social media platforms not only comprise traditional social platforms such as WeChat, microblog and post, but also comprise shopping and payment social software such as Taobao and Paobao.
After the data are obtained, data preprocessing is carried out, wherein the data preprocessing comprises the steps of removing new registered accounts, carrying out data cleaning and structuring on the obtained data, and storing the data in a database.
Personal credit evaluation index system construction step S120
According to the influence of different social media state information on the personal credit condition, five types of hierarchical evaluation indexes are established by utilizing the social media state information, each hierarchical evaluation index comprises a plurality of bottom layer indexes, each evaluation index is assigned to obtain a scoring matrix, and the five types of hierarchical evaluation indexes are account reliability, social activity degree, rule adherence degree, network consumption preference and financial condition respectively.
Specifically, the account reliability, social activity, rule compliance, network consumption preference, and financial status are respectively specifically:
1) the account reliability hierarchical indexes comprise user age, user education degree, user working age, real name authentication, mobile phone number binding, bank card binding quantity and related transaction platform quantity.
The content of an optional evaluation index and several underlying indexes contained are shown in table 1.
TABLE 1 Account reliability hierarchy indexes and bottom layer indexes contained therein
Figure BDA0002755761210000071
2) The social activity hierarchical indexes comprise authenticity of user release information, fluctuation conditions of the number of friends of the user and authenticity of completion of hosting activities, wherein the fulfillment conditions of the hosting activities of the user can reflect basic reputation information of the user, and whether prizes are timely released or not, such as lottery drawing and the like.
Optional social liveness hierarchical index content is shown in table 2, along with several underlying indexes involved.
TABLE 2 social liveness hierarchical index content and underlying index contained therein
Figure BDA0002755761210000081
3) The rule adherence hierarchical index comprises the user transmitting bad information condition, the user releasing content violation times and the group creating violation condition.
TABLE 3 hierarchical index content for rule adherence and included underlying indexes
Figure BDA0002755761210000082
4) And the network consumption preference layering indexes comprise consumption types, group purchase participation times and concerned shops.
Table 4 network consumption preference hierarchical index content and included underlying indexes
Figure BDA0002755761210000083
5) And the financial information hierarchical indexes comprise the balance of the social account, the annual income of the social account, the number of owing times of the installment repayment and the period of owing of the social account.
TABLE 5 financial information hierarchical index content and underlying indexes contained therein
Figure BDA0002755761210000091
Credit index weight acquisition step S130:
in the five types of hierarchical evaluation indexes, importance comparison is carried out on a plurality of bottom indexes in each hierarchical evaluation index, and the weight coefficient of each bottom index in the hierarchical evaluation indexes is determined.
Specifically, the method comprises the following steps:
(1) in each hierarchical index system, carrying out importance comparison on every two of a plurality of bottom layer indexes contained in the hierarchical evaluation index to obtain a judgment matrix C;
wherein, in the comparison of importance, a scale of nine quantile proportion is adoptedijThe comparison result of the ith factor with the j factors is shown, 1-9 show the comparison result of the ith factor with the j factorsEqual to extremely important, 1-1/9 means from equally important to extremely unimportant.
Scale Means of
1 i factor is more important than j factor
3 i factor is slightly more important than j factor
5 The i factor is significantly more important than the j factor
7 i factor is more important than j factor
9 The i factor is extremely important compared to the j factor
2、4、6、8 Scale values corresponding to intermediate states between the above adjacent determinations
For example, the relative importance between the indexes is used to determine the index weight, and the two layers of comparison AB are used to construct a judgment matrix as shown in the following table, where N represents the number of the bottom indexes in the hierarchical index system, i.e. the order of the judgment matrix C.
A B1 B2 …… BN
B1 1 a12 …… a1N
B2 a21 1 …… a2N
…… …… …… 1 ……
BN aN2 aN2 aN2 1
In the above table aijRepresenting the evaluated transaction for A, BiFactor pair BjThe relative importance value of the factors, the diagonal of the matrix is 1, and the upper and lower diagonals are reciprocal.
(2) For the judgment matrix C, a maximum feature root λ max and a feature vector matrix W with respect to the maximum feature root λ max in which a component W is present are obtained using the following formula (1)iIs the weight value corresponding to the bottom layer index
CW＝λmaxW(1)
In an optional embodiment, consistency check is performed on the corresponding scoring matrix when the maximum feature root λ max is obtained, the consistency check is performed to ensure consistency of two-by-two importance degrees of the indexes, and the consistency check is performed when the index proportion is determined to prevent the situation that b is more important than b and c is more important than a from occurring.
And C.I is used as a consistency index and is expressed by a formula, wherein N is the order number of a C matrix, namely the number of the bottom index layers in a certain sub-index layer.
Figure BDA0002755761210000101
And obtaining a consistency index R.I, wherein the R.I can be obtained through query, calculating a consistency parameter C.R through a formula (2), if the C.R is less than or equal to 0.1, judging that the scoring matrix meets the consistency, and if the consistency is not met, adjusting the scoring matrix to reduce the subjective error of the scoring matrix until the scoring matrix is qualified.
Figure BDA0002755761210000102
Final score H calculation step S140:
and multiplying the score of the bottom layer index in each hierarchical evaluation index by the weight value of the corresponding bottom layer index by using an AHP (analytic hierarchy process), and summarizing the five hierarchical evaluation indexes to obtain a final score H.
Examples
(1) The social media status scoring system, 1 total index layer, 5 sub-index layers and 20 bottom index layers are determined as follows:
Figure BDA0002755761210000111
(2) for the research on the relative importance of each index layer, five factors in each index layer are X ═ X1,X2,X3,X4,X5Two-by-two comparison, adopting nine-quantile proportion scale, aijShowing the result of comparing the ith factor with the j factors.
Figure BDA0002755761210000112
Figure BDA0002755761210000121
Determining the index weight for the relative importance among the indexes, wherein the weight obtaining method comprises the following steps:
CW＝λmaxW
and (4) carrying out consistency check to ensure the consistency of the two important degrees of the indexes, and carrying out consistency check to prevent the situation that b is more important than b and c is more important than a from occurring when the specific gravity of the indexes is determined. C.I is used as a consistency index and is expressed by a formula:
Figure BDA0002755761210000122
and then finding out a corresponding consistency index R.I to finally obtain consistency, and judging that the matrix has satisfactory consistency if the consistency C.R is less than or equal to 0.1.
Figure BDA0002755761210000123
The solution using the AHP method is as follows:
social media state evaluation index importance degree comparison table
Figure BDA0002755761210000124
(significance of the transverse index to the longitudinal index: 1-9 points from equally important to very important, 1-1/9, i.e. the reciprocal representation thereof from equally important to very unimportant)
Account reliability importance degree comparison table
Figure BDA0002755761210000125
Figure BDA0002755761210000131
Social activity importance degree comparison table
Figure BDA0002755761210000132
Comparison table of importance degree of rule adherence
Figure BDA0002755761210000133
Network consumption preference importance degree comparison table
Figure BDA0002755761210000134
Financial information importance degree comparison table
Figure BDA0002755761210000135
Social media index scoring table
And multiplying the weight calculated by the AHP analytic hierarchy process by each index in the index scoring table to obtain the final score H of the evaluator.
H＝0.08175*x1+0.33481*x2+0.20107*x3+0.04757*x3+0.33481*x5
X1＝0.06957*x11+0.04018*x12+0.07681*x13+0.21383*x14+0.26647*x15+0.23392*x16+0.09921*x17
X2＝0.16920*x21+0.44343*x22+0.38737x23
X3＝0.53962*x31+0.29696*x32+0.16342*x33
X4＝0.55843*x41+0.12196*x42+0.31962*x43
X5＝0.10780*x51+0.29222*x52+0.18671*x53+0.41327*x54
Compared with the prior art, the personal credit evaluation method based on the social media state provided by the invention has the following advantages:
the invention provides a method for defining various social media data including WeChat, microblog and the like in three aspects of credibility, rule compliance and financial condition and embodies dimensions by combining the characteristics of social media.
The social media state user evaluation system can also cover scenes of job hunting, promotion and the like, and carries out prediction analysis according to the behaviors of the social network to identify which aspect of the social media user is more outstanding in quality.
The invention is not only beneficial to credit evaluation but also beneficial to social users to monitor themselves, improves the social integrity of the users and the rule compliance degree, is beneficial to the purification of network environment, and supervisors can take early warning measures for users with low scores.
While the invention has been described in further detail with reference to specific preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (7)

1. A personal credit evaluation method based on social media state is characterized by comprising the following steps:
social media status information acquisition and preprocessing step S110
Acquiring state information of the same user in a plurality of social media, wherein the state information comprises personal identity information and process information, the personal identity information comprises gender, age, education level, mobile phone number and the like, and the process information comprises information generated in the social contact, communication, entertainment, learning and payment processes of the user;
personal credit evaluation index system construction step S120
Establishing five types of hierarchical evaluation indexes by utilizing social media state information according to the influence of different social media state information on personal credit conditions, wherein each hierarchical evaluation index comprises a plurality of bottom layer indexes, and each evaluation index is assigned to obtain a scoring matrix, and the five types of hierarchical evaluation indexes are account reliability, social activity, rule adherence, network consumption preference and financial conditions respectively;
credit index weight acquisition step S130:
in the five types of hierarchical evaluation indexes, importance comparison is carried out on a plurality of bottom indexes in each hierarchical evaluation index, and the weight coefficient of each bottom index in the hierarchical evaluation indexes is determined;
final score H calculation step S140:
and multiplying the score of the bottom layer index in each hierarchical evaluation index by the weight value of the corresponding bottom layer index by using an AHP (analytic hierarchy process), and summarizing the five hierarchical evaluation indexes to obtain a final score H.
2. The personal credit evaluation method of claim 1, wherein:
in the social media status information acquisition and preprocessing step S110,
the method can cooperate with a plurality of social media platforms, and the state information of the same user in a plurality of social media is obtained through the identification card number, wherein the social media platforms not only comprise traditional social platforms such as WeChat, microblog and sticking bar, but also comprise shopping and payment social software such as Taobao and Paobao.
3. The personal credit evaluation method of claim 1 or 2, wherein:
in the social media status information acquisition and preprocessing step S110,
after the data are obtained, data preprocessing is carried out, wherein the data preprocessing comprises the steps of removing new registered accounts, carrying out data cleaning and structuring on the obtained data, and storing the data in a database.
4. The personal credit evaluation method of claim 1, wherein:
in the step S120 of constructing the personal credit evaluation index system, the account reliability, social activity, rule compliance, network consumption preference, and financial status are respectively specifically:
1) the account reliability hierarchical indexes comprise user age, user education degree, user working age, real name authentication, mobile phone number binding, bank card binding quantity and related transaction platform quantity;
2) the social activity level indexes comprise authenticity of information issued by a user, fluctuation conditions of the number of friends of the user and authenticity of completion of a hosting activity;
3) the rule adherence hierarchical index comprises user transmitting bad information condition, user releasing content violation times and group creating violation condition;
4) network consumption preference layering indexes comprise consumption types, group purchase participation times and concerned shops;
5) and the financial information hierarchical indexes comprise the balance of the social account, the annual income of the social account, the number of owing times of the installment repayment and the period of owing of the social account.
5. The personal credit evaluation method of claim 1, wherein:
the step S130 of acquiring the credit indicator weight specifically includes:
(1) in each hierarchical index system, carrying out importance comparison on every two of a plurality of bottom layer indexes contained in the hierarchical evaluation index to obtain a judgment matrix C;
in the comparison of importance, a scale of nine decimals is usedijThe comparison result of the ith factor to the j factors is shown, 1-9 shows that the ith factor is equally important to extremely important, and 1-1/9 shows that the ith factor is equally important to extremely unimportant;
(2) for the judgment matrix C, a maximum feature root λ max and a feature vector matrix W with respect to the maximum feature root λ max in which a component W is present are obtained using the following formula (1)iIs the weight value corresponding to the bottom layer index
CW＝λmaxW (1)。
6. The personal credit evaluation method of claim 5, wherein:
and (4) carrying out consistency check on the corresponding scoring matrix when the maximum characteristic root lambda max is obtained.
7. The personal credit evaluation method of claim 6, wherein:
the consistency test is as follows: and C.I is used as a consistency index and is expressed by a formula, wherein N is the order number of a C matrix, namely the number of the bottom index layers in a certain sub-index layer.
Figure FDA0002755761200000031
And obtaining a consistency index R.I, wherein the R.I can be obtained through query, calculating a consistency parameter C.R through a formula (2), if the C.R is less than or equal to 0.1, judging that the scoring matrix meets the consistency, and if the consistency is not met, adjusting the scoring matrix to reduce the subjective error of the scoring matrix until the scoring matrix is qualified.
Figure FDA0002755761200000032
CN202011202397.4A 2020-11-02 2020-11-02 Personal credit evaluation method based on social media state Pending CN112465624A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011202397.4A CN112465624A (en) 2020-11-02 2020-11-02 Personal credit evaluation method based on social media state

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011202397.4A CN112465624A (en) 2020-11-02 2020-11-02 Personal credit evaluation method based on social media state

Publications (1)

Publication Number Publication Date
CN112465624A true CN112465624A (en) 2021-03-09

Family

ID=74834877

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011202397.4A Pending CN112465624A (en) 2020-11-02 2020-11-02 Personal credit evaluation method based on social media state

Country Status (1)

Country Link
CN (1) CN112465624A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113327170A (en) * 2021-06-23 2021-08-31 陕西缘著科技有限公司 Social software evaluation method and system, electronic device and storage medium
CN116796079A (en) * 2023-06-30 2023-09-22 深圳市爱彼利科技有限公司 Data processing method and device for social evaluation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110956273A (en) * 2019-11-07 2020-04-03 中信银行股份有限公司 Credit scoring method and system integrating multiple machine learning models
CN111062581A (en) * 2019-11-26 2020-04-24 国网浙江省电力有限公司电力科学研究院 Enterprise client high-voltage value-added service system construction method based on AHP (advanced high Performance packet protocol) hierarchy
CN111126775A (en) * 2019-11-26 2020-05-08 国网浙江省电力有限公司电力科学研究院 Hierarchical analysis method based resident customer value grading model construction method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110956273A (en) * 2019-11-07 2020-04-03 中信银行股份有限公司 Credit scoring method and system integrating multiple machine learning models
CN111062581A (en) * 2019-11-26 2020-04-24 国网浙江省电力有限公司电力科学研究院 Enterprise client high-voltage value-added service system construction method based on AHP (advanced high Performance packet protocol) hierarchy
CN111126775A (en) * 2019-11-26 2020-05-08 国网浙江省电力有限公司电力科学研究院 Hierarchical analysis method based resident customer value grading model construction method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
彭昳偲: ""基于互联网用户行为的个人征信体系的建立及应用研究"", 《中国优秀硕士学位论文全文数据库经济与管理科学辑》, pages 157 - 340 *
虞佳: ""基于社交数据的个人信用评价研究"", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》, pages 159 - 271 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113327170A (en) * 2021-06-23 2021-08-31 陕西缘著科技有限公司 Social software evaluation method and system, electronic device and storage medium
CN116796079A (en) * 2023-06-30 2023-09-22 深圳市爱彼利科技有限公司 Data processing method and device for social evaluation

Similar Documents

Publication Publication Date Title
TWI712981B (en) Risk identification model training method, device and server
Dias Jr et al. Company and project evaluation model for privately promoted infrastructure projects
CN110717816A (en) Artificial intelligence technology-based global financial risk knowledge graph construction method
CN108665159A (en) A kind of methods of risk assessment, device, terminal device and storage medium
CN107330785A (en) A kind of petty load system and method based on the intelligent air control of big data
CN111476660B (en) Intelligent wind control system and method based on data analysis
Campbell et al. Tone at the bottom: Measuring corporate misconduct risk from the text of employee reviews
CN101409634B (en) Quantitative analysis tools and method for internet news influence based on information retrieval
CN112465624A (en) Personal credit evaluation method based on social media state
CN113989019A (en) Method, device, equipment and storage medium for identifying risks
CN110119980A (en) A kind of anti-fraud method, apparatus, system and recording medium for credit
CN111708883A (en) Credit credit limit determination method and device based on machine learning and equipment fingerprint
CN110472806A (en) Financial letter comments System and method for
CN108876193A (en) A kind of air control model building method based on credit score
CN112861003A (en) User portrait construction method and system based on cloud edge collaboration
CN112200656A (en) On-line pre-approval method, device, medium and electronic equipment for house loan
CN113763154A (en) Steel trade supply chain financial risk assessment method based on fuzzy grey evaluation
CN112232950A (en) Loan risk assessment method and device, equipment and computer-readable storage medium
CN109377349A (en) A kind of accrediting amount evaluation method and device based on driving behavior
Li et al. A time attention based fraud transaction detection framework
CN112836137B (en) Character network support degree computing system and method, terminal, equipment and storage medium
Qadri et al. Overflow Effect of COVID‐19 Pandemic on Stock Market Performance: A Study Based on Growing Economy
CN113283806A (en) Enterprise information evaluation method and device, computer equipment and storage medium
CN111582757B (en) Method, device, equipment and computer readable storage medium for analyzing fraud risk
CN113450004A (en) Power credit report generation method and device, electronic equipment and readable storage medium

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