CN110543910A - Credit state monitoring system and monitoring method - Google Patents
Credit state monitoring system and monitoring method Download PDFInfo
- Publication number
- CN110543910A CN110543910A CN201910817319.6A CN201910817319A CN110543910A CN 110543910 A CN110543910 A CN 110543910A CN 201910817319 A CN201910817319 A CN 201910817319A CN 110543910 A CN110543910 A CN 110543910A
- Authority
- CN
- China
- Prior art keywords
- credit
- module
- sample
- classification model
- monitoring
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a credit state monitoring system and a credit state monitoring method, and relates to the field of credit monitoring. The invention comprises the following steps: s1: collecting a large number of credit reports as unmarked samples and preprocessing the samples; s2: setting a credit evaluation index in advance; s3: analyzing and processing the information through a fuzzy optimization model; s4: classifying the associated data to generate a sample set with labels; s5: generating a multi-class classification model by taking part of the sample set as a training set; s6: the rest sample set is used as a test set to test the trained classification model; s7: and importing the labeled sample set into the tested classification model to output a credit state monitoring grade. According to the invention, the collected unmarked samples are primarily screened through the fuzzy optimization model, the sample set is subjected to SVM classification training to generate the classification model, and the rest sample sets are tested on the classification model to obtain the optimal classification model, so that the enterprise credit evaluation efficiency is improved, and the monitoring strength is enhanced.
Description
Technical Field
the invention belongs to the technical field of credit monitoring, and particularly relates to a credit state monitoring system and a credit state monitoring method.
Background
Corporate credit broadly refers to the credit that one corporate legal entity grants to another corporate legal entity, in essence being the debit and credit of money from the buyer enterprise by the seller enterprise. It includes the credit sale of the manufacturer to the client of enterprise legal person, i.e. the product credit sale. In the product credit process, the credit granting parties are typically material suppliers, product manufacturers and wholesalers, while the purchasers are beneficiaries of product credit, which are various business customers or agents. The buyer receives the credit granted by the seller on behalf of his business. Corporate credit also refers to credit to businesses in commercial banks, financial companies, other financial institutions, and credit generated using trades other than pay-as-you-go and prepaid.
the credit rating of an enterprise has great influence on the operation condition of the enterprise, and the credit rating of the enterprise is also a key concern object of competing enterprises, but the existing novel enterprise credit management platform cannot evaluate the credit rating of the enterprise perfectly, so that the public is not convenient to clearly know the credit condition of the enterprise, and the public is also not convenient to monitor the enterprise credit.
Disclosure of Invention
the invention aims to provide a credit state monitoring system and a credit state monitoring method.
in order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a credit state monitoring system, which comprises a sample acquisition unit, a fuzzy optimization unit and a monitoring and early warning unit;
The sample acquisition unit, the fuzzy optimization unit and the monitoring and early warning unit are sequentially connected;
The sample acquisition unit comprises an acquisition module and a sample pretreatment module; the module acquisition unit is used for acquiring the credit report through a web crawler and extracting unmarked samples; the sample preprocessing module is used for performing index screening on the extracted unmarked samples;
The fuzzy optimization unit comprises a fuzzy optimization module, a credit index setting module and a label calibration module; the fuzzy optimization module is used for making a fuzzy optimization model to analyze and process information and searching for the relation among data; the credit index setting module is used for setting a credit evaluation index in advance; the label calibration module is used for classifying data to generate a sample set with labels;
the detection early warning unit comprises an SVM module, a classification model module and an output module; the SVM module is used for carrying out SVM algorithm processing on the sample set with the label; the classification model module is used for training a classification model through a binary tree multi-class classification model; and the output module is used for inputting the standard sample to the trained model and outputting the credit state monitoring grade.
Preferably, the credit indicator setting module performs calculation according to different credit indicator calculation rules to obtain the tag type.
Preferably, the labeled sample set generated by the label calibration module is divided into a training set and a test set; the training set is used for providing sample materials required by the training model for the SVM module; the test set is used for providing test sample materials for testing for the trained classification model.
Preferably, the credit status monitoring levels include four levels of credit status security, credit status reminder, credit status warning and credit status danger, and each level corresponds to a preset threshold.
preferably, the SVM module is configured to construct a hyperplane function to segment two different types of samples, and the specific classification function is as follows:
In the formula, K (xi. xj) is a kernel function.
the invention relates to a credit state monitoring method, which comprises the following steps:
Step S1: collecting a large number of credit reports as unmarked samples and preprocessing the samples;
Step S2: setting a credit evaluation index in advance;
step S3: analyzing and processing the information through a fuzzy optimization model, and searching for the relation between data;
step S4: classifying the associated data to generate a sample set with labels;
Step S5: a part of sample sets are used as training sets to generate multi-class classification models;
step S6: the other part of the sample set is used as a test set to test the trained classification model;
Step S7: and importing the labeled sample set into the tested classification model to output a credit state monitoring grade.
the invention has the following beneficial effects:
According to the invention, the collected unmarked samples are primarily screened through the fuzzy optimization model to generate the sample set with the labels, one part of the sample set with the labels is subjected to SVM classification training to generate the classification model, the rest sample sets are tested on the classification model to obtain the optimal classification model, the samples with the labels are input into the trained classification model to output the credit state monitoring grade, the enterprise credit evaluation efficiency is improved, and the monitoring strength is enhanced.
of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
drawings
in order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating a credit status monitoring method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
the invention relates to a credit state monitoring system, which comprises a sample acquisition unit, a fuzzy optimization unit and a monitoring and early warning unit;
the sample acquisition unit, the fuzzy optimization unit and the monitoring and early warning unit are sequentially connected;
The sample acquisition unit comprises an acquisition module and a sample pretreatment module; the module acquisition unit is used for acquiring the credit report through the web crawler and extracting unmarked samples; the sample preprocessing module is used for screening indexes of extracted unmarked samples, performing text preprocessing on the report, including Chinese word segmentation, stop word removal, feature extraction and matching labels, and matching according to various preset indexes;
The fuzzy optimization unit comprises a fuzzy optimization module, a credit index setting module and a label calibration module; the fuzzy optimization module is used for making a fuzzy optimization model to analyze and process the information and searching the relation among the data; the credit index setting module is used for setting a credit evaluation index in advance; the label calibration module is used for classifying the data to generate a sample set with labels;
The detection early warning unit comprises an SVM module, a classification model module and an output module; the SVM module is used for carrying out SVM algorithm processing on the sample set with the label; the classification model module is used for training a classification model through a binary tree multi-class classification model; and the output module is used for inputting the standard samples to the trained model and outputting the credit state monitoring grade.
the credit index setting module calculates to obtain the label type according to different credit index calculation rules.
The label-containing sample set generated by the label calibration module is divided into a training set and a test set; the training set is used for providing sample materials required by the training model for the SVM module; the test set is used for providing test sample materials for testing for the trained classification model.
The credit state monitoring levels comprise four levels of credit state safety, credit state reminding, credit state warning and credit state danger, and each level corresponds to a preset threshold value.
the SVM module is used for constructing a hyperplane function to divide two different samples, and the specific optimal classification function is as follows:
In the formula, K (xi. xj) is a kernel function.
referring to fig. 1, the present invention is a credit status monitoring method, including the following steps:
step S1: collecting a large number of credit reports as unmarked samples and preprocessing the samples;
step S2: setting a credit evaluation index in advance;
Step S3: analyzing and processing the information through a fuzzy optimization model, and searching for the relation between data;
step S4: classifying the associated data to generate a sample set with labels;
step S5: a part of sample sets are used as training sets to generate multi-class classification models;
step S6: the other part of the sample set is used as a test set to test the trained classification model;
Step S7: and importing the labeled sample set into the tested classification model to output a credit state monitoring grade.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (6)
1. a credit state monitoring system and a monitoring method comprise a sample acquisition unit, a fuzzy optimization unit and a monitoring and early warning unit, and are characterized in that:
the sample acquisition unit, the fuzzy optimization unit and the monitoring and early warning unit are sequentially connected;
the sample acquisition unit comprises an acquisition module and a sample pretreatment module; the module acquisition unit is used for acquiring the credit report through a web crawler and extracting unmarked samples; the sample preprocessing module is used for performing index screening on the extracted unmarked samples;
the fuzzy optimization unit comprises a fuzzy optimization module, a credit index setting module and a label calibration module; the fuzzy optimization module is used for making a fuzzy optimization model to analyze and process information and searching for the relation among data; the credit index setting module is used for setting a credit evaluation index in advance; the label calibration module is used for classifying data to generate a sample set with labels;
the detection early warning unit comprises an SVM module, a classification model module and an output module; the SVM module is used for carrying out SVM algorithm processing on the sample set with the label; the classification model module is used for training a classification model through a binary tree multi-class classification model; and the output module is used for inputting the standard sample to the trained model and outputting the credit state monitoring grade.
2. The system according to claim 1, wherein the credit indicator setting module computes the tag type according to different credit indicator computation rules.
3. The system of claim 1, wherein the labeled sample set generated by the label calibration module is divided into a training set and a testing set; the training set is used for providing sample materials required by the training model for the SVM module; the test set is used for providing test sample materials for testing for the trained classification model.
4. The system of claim 1, wherein the credit monitoring levels comprise four levels of credit security, credit reminder, credit warning, and credit danger, and each level corresponds to a preset threshold.
5. the system of claim 1, wherein the SVM module is configured to construct a hyperplane function to segment two different classes of samples, the classification function being as follows:
in the formula, K (xi. xj) is a kernel function.
6. a method of monitoring a credit status monitoring system as claimed in claims 1-5, comprising the steps of:
step S1: collecting a large number of credit reports as unmarked samples and preprocessing the samples;
step S2: setting a credit evaluation index in advance;
step S3: analyzing and processing the information through a fuzzy optimization model, and searching for the relation between data;
Step S4: classifying the associated data to generate a sample set with labels;
Step S5: a part of sample sets are used as training sets to generate multi-class classification models;
step S6: the other part of the sample set is used as a test set to test the trained classification model;
Step S7: and importing the labeled sample set into the tested classification model to output a credit state monitoring grade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910817319.6A CN110543910A (en) | 2019-08-30 | 2019-08-30 | Credit state monitoring system and monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910817319.6A CN110543910A (en) | 2019-08-30 | 2019-08-30 | Credit state monitoring system and monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110543910A true CN110543910A (en) | 2019-12-06 |
Family
ID=68712463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910817319.6A Withdrawn CN110543910A (en) | 2019-08-30 | 2019-08-30 | Credit state monitoring system and monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543910A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365186A (en) * | 2020-11-27 | 2021-02-12 | 中国电建集团海外投资有限公司 | Health degree evaluation method and system for electric power information system |
| CN113962568A (en) * | 2021-10-26 | 2022-01-21 | 天元大数据信用管理有限公司 | Model label labeling method, device and medium based on support vector machine |
-
2019
- 2019-08-30 CN CN201910817319.6A patent/CN110543910A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365186A (en) * | 2020-11-27 | 2021-02-12 | 中国电建集团海外投资有限公司 | Health degree evaluation method and system for electric power information system |
| CN113962568A (en) * | 2021-10-26 | 2022-01-21 | 天元大数据信用管理有限公司 | Model label labeling method, device and medium based on support vector machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yeh et al. | Going-concern prediction using hybrid random forests and rough set approach | |
| CA3063580A1 (en) | Classifier training method and apparatus, electronic device and computer readable medium | |
| CN103703487B (en) | Information identifying method and system | |
| Gupta et al. | Financial statement fraud detection using text mining | |
| CN109360089A (en) | Credit risk prediction technique and device | |
| Noviandy et al. | Credit Card Fraud Detection for Contemporary Financial Management Using XGBoost-Driven Machine Learning and Data Augmentation Techniques | |
| Brennan | A comprehensive survey of methods for overcoming the class imbalance problem in fraud detection | |
| US20230419402A1 (en) | Systems and methods of optimizing machine learning models for automated anomaly detection | |
| CN109815480B (en) | Data processing method and device and storage medium | |
| Braun et al. | Improving card fraud detection through suspicious pattern discovery | |
| Altaheri et al. | Exploring machine learning models to predict harmonized system code | |
| CN110543910A (en) | Credit state monitoring system and monitoring method | |
| Wu et al. | TEDM-PU: A tax evasion detection method based on positive and unlabeled learning | |
| Jaroonchokanan et al. | Dynamics of hierarchical clustering in stocks market during financial crises | |
| CN112581271B (en) | Merchant transaction risk monitoring method, device, equipment and storage medium | |
| CN111125345B (en) | Data application method and device | |
| CN114495224A (en) | Credit risk determination method and device | |
| CN113837836A (en) | Model recommendation method, device, equipment and storage medium | |
| Lee et al. | Application of machine learning in credit risk scorecard | |
| Vijayarani et al. | Predicting Stock Market Using Machine Learning Algorithms | |
| CN115713399B (en) | User credit evaluation system combined with third-party data source | |
| CN117874597A (en) | Federal learning finance sensitive data identification and processing system | |
| Folasade et al. | Development of a Credit Card Fraud Detection Model | |
| CN113076352A (en) | Auditing method, electronic device and storage medium | |
| Saket et al. | Cost Sensitive Approach to Ethereum Transactions Fraud Detection using Machine Learning |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191206 |
|
| WW01 | Invention patent application withdrawn after publication |