CN111400375A - Business opportunity mining method and device based on financial service data - Google Patents
Business opportunity mining method and device based on financial service data Download PDFInfo
- Publication number
- CN111400375A CN111400375A CN202010196806.8A CN202010196806A CN111400375A CN 111400375 A CN111400375 A CN 111400375A CN 202010196806 A CN202010196806 A CN 202010196806A CN 111400375 A CN111400375 A CN 111400375A
- Authority
- CN
- China
- Prior art keywords
- data
- financial
- business
- modeling
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000005065 mining Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 23
- 230000006399 behavior Effects 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 238000003064 k means clustering Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A business mining method based on financial business data comprises the following steps: receiving and storing data, namely receiving and storing financial service data after a user uses financial software; existing financial transaction data, including order data, financial data, and user behavior data; the method comprises the steps of demand analysis, namely obtaining the existing demands for analysis, obtaining the classification of financial business experts, and forming modeling data according to the classification; model training, namely receiving modeling data and performing clustering analysis by adopting K _ means unsupervised machine learning; and operation practice, namely acquiring a clustering analysis result, analyzing a user label by combining operation services, and formulating an operation scheme for testing.
Description
Technical Field
The invention relates to the technical field of computer networks, in particular to a business mining method and device based on middle and small micro-enterprise financial business data.
Background
For the existing customer label analysis of financial software, the existing customer information, behavior information and financial information are not dynamically analyzed and processed based on traditional experience, and efficient customer label construction is difficult to achieve. It has been difficult to meet the rapidly changing operational demands for existing customer labeling methods.
Aiming at the existing problem of customer label definition, the label device for fast iterating the user business opportunity is realized, and the label device has good practical significance for business opportunities such as regular customer relationship maintenance, repeated customer purchase, continuous purchase and the like.
Disclosure of Invention
Aiming at the problems of empriezation of the conventional user business opportunity label and slow updating iteration, the invention provides a method and a device for mining the business opportunity label based on quick iteration of financial data,
the invention provides a business opportunity mining method based on financial service data, which comprises the following steps:
receiving and storing data, namely receiving and storing financial service data after a user uses financial software; existing financial transaction data, including order data, financial data, and user behavior data;
the method comprises the steps of demand analysis, namely obtaining the existing demands for analysis, obtaining the classification of financial business experts, and forming modeling data according to the classification;
model training, namely receiving modeling data and performing clustering analysis by adopting K _ means unsupervised machine learning;
and operation practice, namely acquiring a clustering analysis result, analyzing a user label by combining operation services, and formulating an operation scheme for testing.
In an embodiment of the present disclosure, the requirement analysis includes classifying requirements by analyzing the operation requirements in combination with the previous user tag data and operation flow, and determining to perform ET L operation on the existing data according to the requirement classification to form financial modeling index data.
In an embodiment of the present disclosure, the model training includes step 1, determining a cluster K value using a pedigree cluster map and business requirements.
In an embodiment of the present disclosure, the model training includes step 2, training a K _ means clustering model to cluster modeling index data, and dividing the modeling index data into K clusters.
In an embodiment of the present disclosure, the model training includes step 3, marking the modeling index data according to clustering, and analyzing density characteristics of different types of data.
In an embodiment of the disclosure, the model training includes step 4, classifying different modeling index density characteristics, and forming a business opportunity label by combining a current label system and an operation process.
The invention also provides a business machine mining device based on financial service data, which comprises:
the data receiving and storing unit is used for receiving and storing the financial service data after the user uses the financial software; existing financial transaction data, including order data, financial data, and user behavior data;
the demand analysis unit is used for acquiring the existing demand for analysis, acquiring the classification of the financial business experts and forming modeling data according to the classification;
the model training unit is used for receiving modeling data and performing clustering analysis by adopting K _ means unsupervised machine learning; and the operation practice unit is used for acquiring the clustering analysis result, analyzing the user label by combining the operation service, and formulating an operation scheme for testing.
In an embodiment of the present disclosure, the requirement analysis unit includes a processor configured to classify requirements according to analysis operation requirements and user tag data and operation procedures before the analysis operation requirements are combined, and determine to perform ET L operation on existing data according to the requirement classification, so as to form financial modeling index data.
In an embodiment of the present disclosure, the model training unit includes a module for determining a cluster K value using a pedigree cluster map and a business requirement; training a K _ means clustering model to cluster modeling index data, and dividing the modeling index data into K clusters; marking the modeling index data according to clustering, and analyzing the density characteristics of different types of data; and classifying different modeling index density characteristics, and combining the current label system and the operation process to form a business opportunity label.
The business opportunity mining method and device based on financial service data provided by the invention have the following technical effects:
analyzing operation requirements and existing customer labels based on existing database financial data, summarizing existing business label experience, mining enterprise financial business data by using K _ means unsupervised machine learning, assigning a simple operation scheme to perform label testing, continuously updating business labels and quickly updating a financial enterprise customer label system.
The technical solutions of the embodiments of the present invention are further described in detail with reference to the accompanying drawings and embodiments.
Drawings
FIG. 1 is an overall flow diagram of business mining;
FIG. 2 is a detailed flow diagram of business mining.
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. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention provides a business opportunity mining method based on financial service data, which comprises the following steps as shown in figure 1:
receiving and storing data, namely receiving and storing financial service data after a user uses financial software; existing financial transaction data, including order data, financial data, and user behavior data, such as node 0 in FIG. 1.
And (3) analyzing the demand, acquiring the existing demand for analysis, acquiring the classification of the financial business experts, and forming modeling data according to the classification, such as nodes 1 and 2 in the figure 1.
And (3) model training, receiving modeling data, and performing clustering analysis by adopting K _ means unsupervised machine learning, such as 3 nodes in the figure 1.
And operation practice, namely acquiring a clustering analysis result, analyzing a user label by combining operation services, and formulating an operation scheme for testing. As shown in fig. 1, nodes 4,5,6, and 7 generate user tags through model analysis, apply the user tags to obtain business opportunities such as regular maintenance of customer relationship, repeated customer purchase, and continuous purchase, analyze the application results, and feed back the application results as expert experience to the device, thereby implementing fast iteration of the user business opportunity tags.
In the method of this embodiment, the more detailed flow includes the following steps:
and (3) demand analysis, namely classifying demands by combining the analysis operation demands with the previous user tag data and operation flow, and determining to perform ET L operation on the existing data according to the demand classification to form financial modeling index data, such as a node 1 in fig. 2.
Model training, namely establishing k _ means modeling by using modeling data, wherein the k _ means modeling comprises the following steps:
step 1, firstly, modeling index data, and determining a clustering K value by utilizing a pedigree clustering graph and a service requirement, such as 2 nodes in FIG. 2;
step 2, training a K _ means clustering model to cluster modeling index data, and dividing the modeling index data into K clusters, such as 3 nodes in the graph 2;
step 3, marking the modeling index data according to clustering, and analyzing the density characteristics of different types of data, such as 4 nodes in the graph 2;
and 4, classifying different modeling index density characteristics, and combining the current label system and the operation process to form a business opportunity label. As shown in fig. 2 at nodes 5.1, 5.2, 5.3, etc., the modeling indicators may be classified into major categories such as financial indicators, behavior indicators, and basic indicators. Financial indicators may include indicators for property, profit, and cash flow in the month. The behavior indicators may include indicators of the number of credentials, the number of logins, and the time of the last purchase. The basic indexes may include indexes of industry, number of workers, and the like. And performing density analysis on various indexes, and forming a user business label.
And operation practice, namely, the business opportunity label of the model analysis is tested by a specified operation scheme in combination with the operation flow stage, and the business opportunity label is fed back to the label library. As shown in fig. 2, nodes 6.1, 6.2, 6.3 and the like, the business opportunity tags can be divided into high-value tags, low-value tags, important development tags, loss early warning tags and the like, so that fast iteration of the user business opportunity tags is realized, and the method has good practical significance for business opportunities such as regular maintenance of customer relations, repeated purchase of customers, continuous purchase and the like.
Another embodiment of the present invention provides a business machine mining device based on financial transaction data, as shown in fig. 1, including:
the data receiving and storing unit is used for receiving and storing the financial service data after the user uses the financial software; existing financial transaction data, including order data, financial data, and user behavior data, such as node 0 in FIG. 1.
And the requirement analysis unit is used for acquiring the existing requirements for analysis, acquiring the classification of the financial business experts and forming modeling data according to the classification, such as nodes 1 and 2 in the figure 1.
And the model training unit is used for receiving modeling data and performing clustering analysis by adopting K _ means unsupervised machine learning, such as 3 nodes in the figure 1.
And the operation practice unit is used for acquiring the clustering analysis result, analyzing the user label by combining the operation service, and making an operation scheme for testing, such as nodes 4,5,6 and 7 in the figure 1.
The method and the device analyze the operation requirements and the existing client labels based on the existing database financial data, summarize the experience of the existing business labels, utilize K _ means unsupervised machine learning to mine the enterprise financial service data, specify a simple operation scheme to perform label testing, continuously update the business labels and quickly update the financial enterprise client label system, can realize effective verification of the experience problem of the client labels, can realize quick update of the enterprise financial client label system, can improve the operation efficiency of enterprises and increase the profit of the enterprises.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and is not to be construed as limiting the invention since the present invention is more easily understood by those skilled in the art, and any modifications, equivalents and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A business opportunity mining method based on financial business data is characterized by comprising the following steps:
receiving and storing data, namely receiving and storing financial service data after a user uses financial software; existing financial transaction data, including order data, financial data, and user behavior data;
the method comprises the steps of demand analysis, namely obtaining the existing demands for analysis, obtaining the classification of financial business experts, and forming modeling data according to the classification;
model training, namely receiving modeling data and performing clustering analysis by adopting K _ means unsupervised machine learning;
and operation practice, namely acquiring a clustering analysis result, analyzing a user label by combining operation services, and formulating an operation scheme for testing.
2. The method of claim 1, wherein the demand analysis comprises classifying demands for analyzing operational demands in combination with previous user tag data and operational procedures, and determining ET L operations on existing data according to the demand classification to form financial modeling index data.
3. The method of claim 1, wherein the model training comprises a step 1 of determining a cluster K value using a pedigree cluster map and business requirements.
4. The method of claim 3, wherein the model training comprises a step 2 of training a K _ means clustering model to cluster modeling index data into K clusters.
5. The method of claim 4, wherein the model training comprises a step 3 of marking modeling index data according to clustering and analyzing density characteristics of different types of data.
6. The method of claim 5, wherein the model training comprises a step 4 of classifying different modeling index density characteristics and forming business opportunity labels by combining a current label system and an operation process.
7. A business machine mining device based on financial transaction data, comprising:
the data receiving and storing unit is used for receiving and storing the financial service data after the user uses the financial software; existing financial transaction data, including order data, financial data, and user behavior data;
the demand analysis unit is used for acquiring the existing demand for analysis, acquiring the classification of the financial business experts and forming modeling data according to the classification;
the model training unit is used for receiving modeling data and performing clustering analysis by adopting K _ means unsupervised machine learning; and the operation practice unit is used for acquiring the clustering analysis result, analyzing the user label by combining the operation service, and formulating an operation scheme for testing.
8. The apparatus of claim 7, wherein the requirement analysis unit comprises a data processing unit for classifying requirements according to analysis operation requirements, combined with previous user tag data and operation flow, and performing ET L operation on existing data according to requirement classification determination to form financial modeling index data.
9. The apparatus of claim 7, wherein the model training unit comprises means for determining a cluster K value using a pedigree cluster map and business requirements; training a K _ means clustering model to cluster modeling index data, and dividing the modeling index data into K clusters; marking the modeling index data according to clustering, and analyzing the density characteristics of different types of data; and classifying different modeling index density characteristics, and combining the current label system and the operation process to form a business opportunity label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010196806.8A CN111400375A (en) | 2020-03-19 | 2020-03-19 | Business opportunity mining method and device based on financial service data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010196806.8A CN111400375A (en) | 2020-03-19 | 2020-03-19 | Business opportunity mining method and device based on financial service data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111400375A true CN111400375A (en) | 2020-07-10 |
Family
ID=71432711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010196806.8A Pending CN111400375A (en) | 2020-03-19 | 2020-03-19 | Business opportunity mining method and device based on financial service data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400375A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113204603A (en) * | 2021-05-21 | 2021-08-03 | 中国光大银行股份有限公司 | Method and device for marking categories of financial data assets |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503438A (en) * | 2016-10-20 | 2017-03-15 | 上海科瓴医疗科技有限公司 | A kind of H RFM user modeling method and system for pharmacy member analysis |
| CN106548381A (en) * | 2016-12-19 | 2017-03-29 | 武汉理工数字传播工程有限公司 | Intelligent subscriber tag systems and implementation method |
| CN108171553A (en) * | 2018-01-17 | 2018-06-15 | 焦点科技股份有限公司 | The potential customers' digging system and method for a kind of periodic service or product |
| CN108363821A (en) * | 2018-05-09 | 2018-08-03 | 深圳壹账通智能科技有限公司 | A kind of information-pushing method, device, terminal device and storage medium |
| CN108664653A (en) * | 2018-05-18 | 2018-10-16 | 拓普暨达（广州）基因精准医疗科技有限公司 | A kind of Medical Consumption client's automatic classification method based on K-means |
| CN109242514A (en) * | 2018-08-28 | 2019-01-18 | 腾讯科技（深圳）有限公司 | Client's label recommendation method, device and system |
| CN109685581A (en) * | 2019-01-03 | 2019-04-26 | 江苏方天电力技术有限公司 | A kind of large power customers electricity consumption behavior analysis method based on label clustering technology |
-
2020
- 2020-03-19 CN CN202010196806.8A patent/CN111400375A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503438A (en) * | 2016-10-20 | 2017-03-15 | 上海科瓴医疗科技有限公司 | A kind of H RFM user modeling method and system for pharmacy member analysis |
| CN106548381A (en) * | 2016-12-19 | 2017-03-29 | 武汉理工数字传播工程有限公司 | Intelligent subscriber tag systems and implementation method |
| CN108171553A (en) * | 2018-01-17 | 2018-06-15 | 焦点科技股份有限公司 | The potential customers' digging system and method for a kind of periodic service or product |
| CN108363821A (en) * | 2018-05-09 | 2018-08-03 | 深圳壹账通智能科技有限公司 | A kind of information-pushing method, device, terminal device and storage medium |
| CN108664653A (en) * | 2018-05-18 | 2018-10-16 | 拓普暨达（广州）基因精准医疗科技有限公司 | A kind of Medical Consumption client's automatic classification method based on K-means |
| CN109242514A (en) * | 2018-08-28 | 2019-01-18 | 腾讯科技（深圳）有限公司 | Client's label recommendation method, device and system |
| CN109685581A (en) * | 2019-01-03 | 2019-04-26 | 江苏方天电力技术有限公司 | A kind of large power customers electricity consumption behavior analysis method based on label clustering technology |
Non-Patent Citations (1)
| Title |
|---|
| 郝志峰: "数据科学与数学建模", vol. 1, pages: 41 - 42 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113204603A (en) * | 2021-05-21 | 2021-08-03 | 中国光大银行股份有限公司 | Method and device for marking categories of financial data assets |
| CN113204603B (en) * | 2021-05-21 | 2024-02-02 | 中国光大银行股份有限公司 | Category labeling method and device for financial data assets |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11087245B2 (en) | Predictive issue detection | |
| US20170109676A1 (en) | Generation of Candidate Sequences Using Links Between Nonconsecutively Performed Steps of a Business Process | |
| US20170109668A1 (en) | Model for Linking Between Nonconsecutively Performed Steps in a Business Process | |
| US20170109667A1 (en) | Automaton-Based Identification of Executions of a Business Process | |
| CN111915366B (en) | User portrait construction method, device, computer equipment and storage medium | |
| CN110874715A (en) | Detecting reporting-related problems | |
| CN112527994A (en) | Emotion analysis method, emotion analysis device, emotion analysis equipment and readable storage medium | |
| US20190080352A1 (en) | Segment Extension Based on Lookalike Selection | |
| CN111489201A (en) | Method, device and storage medium for analyzing customer value | |
| CN111931809A (en) | Data processing method and device, storage medium and electronic equipment | |
| CN111783039A (en) | Risk determination method, risk determination device, computer system and storage medium | |
| CN113780329A (en) | Method, apparatus, server and medium for identifying data anomalies | |
| US20170109640A1 (en) | Generation of Candidate Sequences Using Crowd-Based Seeds of Commonly-Performed Steps of a Business Process | |
| CN109684198B (en) | Method, device, medium and electronic equipment for acquiring data to be tested | |
| CN111062600A (en) | Model evaluation method, system, electronic device, and computer-readable storage medium | |
| CN114997916A (en) | Prediction method, system, electronic device and storage medium of potential user | |
| CN111400375A (en) | Business opportunity mining method and device based on financial service data | |
| US20170109637A1 (en) | Crowd-Based Model for Identifying Nonconsecutive Executions of a Business Process | |
| CN115146653B (en) | Dialogue scenario construction method, device, equipment and storage medium | |
| Tao | Analysis method for customer value of aviation big data based on LRFMC model | |
| CN111582313A (en) | Sample data generation method and device and electronic equipment | |
| CN116795978A (en) | Complaint information processing method and device, electronic equipment and medium | |
| CN112685374A (en) | Log classification method and device and electronic equipment | |
| US20200286104A1 (en) | Platform for In-Memory Analysis of Network Data Applied to Profitability Modeling with Current Market Information | |
| US20230230081A1 (en) | Account identification method, apparatus, electronic device and computer readable 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 |