CN111428092A - Accurate bank marketing method based on graph model - Google Patents
Accurate bank marketing method based on graph model Download PDFInfo
- Publication number
- CN111428092A CN111428092A CN202010201982.6A CN202010201982A CN111428092A CN 111428092 A CN111428092 A CN 111428092A CN 202010201982 A CN202010201982 A CN 202010201982A CN 111428092 A CN111428092 A CN 111428092A
- Authority
- CN
- China
- Prior art keywords
- bank
- graph model
- community
- marketing
- user
- 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.)
- Granted
Links
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a bank accurate marketing method based on a graph model, which comprises the following steps: constructing a graph model according to the transfer transaction data and the asset use information of each bank user; optimizing the graph model to construct a graph model with a user community; and carrying out bank precision marketing according to the graph model with the user community. The embodiment of the invention provides a bank accurate marketing method based on a graph model, which is used for establishing the graph model of fund transaction behaviors based on the relevance and the similarity of the fund transaction behaviors among bank customers, can be used for positioning the bank customer groups and recommending bank products, finds the current customer groups and customers with larger influence to popularize, and improves marketing conversion to a certain extent. In addition, the graph model generation characteristics, the community where the client is located, the community related attributes and the attributes of the client in the community can be used as a supplement of a bank client label system, so that data analysis is facilitated, and interpretability is enhanced.
Description
Technical Field
The invention relates to the technical field of banking business management, in particular to a precise bank marketing method based on a graph model.
Background
Generally, banks mainly adopt modes of telemarketing, social marketing, active customer visiting, business manager visiting and the like to carry out business promotion. In the actual operation process, the popularization methods can meet various problems, such as fraud risk of stranger marketing, limitation of channel expansion to human input, lack of client information, incapability of providing scene and personalized services and the like. These problems result in inefficient business marketing transformations for the bank.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a bank precision marketing method based on a graph model.
The embodiment of the invention provides a bank accurate marketing method based on a graph model, which comprises the following steps:
constructing a graph model according to the transfer transaction data and the asset use information of each bank user;
optimizing the graph model to construct a graph model with a user community;
and carrying out bank precision marketing according to the graph model with the user community.
Optionally, the constructing a graph model according to transaction data and asset use information of each bank user includes:
1) designing a graph model:
transfer transaction data among all bank customers are converted to form a transfer transaction relation network among the bank customers, the transfer transaction relation network takes bank cards as nodes, transfer transactions among the bank cards as relation edges, the nodes are customer nodes, and the relation edges are connection edges among the customer nodes; wherein the attributes of the client nodes are corresponding client portrait data;
2) and (3) realizing a graph model:
2-1) data preparation:
sample selection is carried out by setting composite conditions of time and space, and account transfer transaction data and asset use information of all bank users are obtained;
2-2) data preprocessing:
screening the transfer transaction data of each bank user, and reserving effective bank transfer transaction data;
2-3) node generation:
setting the selection of node granularity, wherein the selection comprises the steps of taking a customer as a node and taking a bank card as a node, and the granularity is determined by a service scene;
2-4) generating a relation edge:
evaluating the relationship between the client and the client according to the transaction behavior, and generating a relationship edge for the account transfer transaction data by adopting rules, statistics or clustering and the like;
3) pruning a graph model:
and analyzing the nodes and the relation edges on the graph by adopting the technologies of statistics, clustering, abnormal value processing and the like, and deleting outlier samples which do not accord with data distribution.
Optionally, the optimizing the graph model to construct a graph model with a user community includes:
1) establishing a user community:
analyzing the topological structure of the transfer transaction relationship network by adopting a community discovery algorithm, and dividing the graph into a plurality of nodes and subsets of relationship edges;
2) user community post-processing:
when the scale of the user community is larger than a certain threshold value, analyzing the user community and dividing the user community into communities with relatively small and balanced scale;
3) constructing a user community portrait:
analyzing the node attribute and the relation edge attribute of the user community by adopting a rule, statistic or clustering technology, and establishing a community label;
4) and (3) evaluating the influence of the nodes:
and analyzing the community, finding out the node with the maximum influence, determining the influence evaluation result of the node, and adding the node influence evaluation result into the community label.
Optionally, the performing bank precision marketing according to a graph model with a user community includes:
1) the graph model is used for accurate marketing of banks:
defining combination conditions according to business requirements, searching user communities meeting the conditions according to the combination conditions, and then carrying out product marketing measures on clients with large influence in the communities;
2) graph model generation features as a complement to the customer label hierarchy:
according to the community where the client is located, the community label and the attribute of the client in the community, marketing process analysis, marketing data analysis and other related data analysis are supported;
3) graph model generation features learning models for bank customer marketing:
and generating features according to the graph model to form a feature sample set for establishing a learning model for marketing of bank customers.
The embodiment of the invention provides a bank accurate marketing method based on a graph model, which is used for establishing the graph model of fund transaction behaviors based on the relevance and the similarity of the fund transaction behaviors among bank customers, can be used for positioning the bank customer groups and recommending bank products, finds the current customer groups and customers with larger influence to popularize, and improves marketing conversion to a certain extent. In addition, the graph model generation characteristics, the community where the client is located, the community related attributes and the attributes of the client in the community can be used as a supplement of a bank client label system, so that data analysis is facilitated, and interpretability is enhanced. The graph model generation features, including graph attributes, graph indexes and graph vectors, can be combined with existing features or form a sample set, and are used for enhancing the overall effect of the learning model in a bank customer marketing scene.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of an embodiment of a graph model-based bank precision marketing method of the present invention;
FIG. 2 is a diagram illustrating a user community partitioned in the graph model of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 shows a diagram model-based bank precision marketing method according to an embodiment of the present invention, which includes:
s11, constructing a graph model according to the transfer transaction data and the asset use information of each bank user;
s12, optimizing the graph model, and constructing a graph model with a user community;
and S13, carrying out bank accurate marketing according to the graph model with the user community.
With respect to step S11, it should be noted that, in the embodiment of the present invention, the following is specifically performed:
1) designing a graph model:
and transforming the transfer transaction data among the bank customers to form a transfer transaction relationship network among the bank customers. The implicit assumption here is that when the transfer transaction between the customers meets certain conditions, which are determined by the business scenario, a stable association exists between the customers.
The transfer transaction relation network takes bank cards as nodes, transfer transactions among the bank cards as relation edges, the nodes are customer nodes, and the relation edges are connection edges among the customer nodes.
Here, the object granularity of a node is determined by the traffic scenario: the fine granularity adopts the design mode of a bank card node, and the coarse granularity adopts the design mode of a customer node.
The attributes of the node are mainly client-related image data, including but not limited to important attributes of the user (home condition, work condition, car-of-house mobile phone, etc.), asset attributes (deposit, financing, securities, insurance, etc.), liability attributes (small cash credit, consumption credit, house credit, etc.), transacted business (credit card, account level, personal credit, etc.), and the like. Attributes for relationship edges include, but are not limited to, transaction behavior statistics (transaction amount, transaction frequency, transaction amount, mutual transactions, transaction time, etc.), transaction relationship quantification (transaction closeness, integrated intimacy, etc.), other data (family relationship, job relationship, account transfer relationship, etc.). And configuring the attributes of the nodes and the relation edges according to the service scene and the current situation of the warehouse.
2) And (3) realizing a graph model:
2-1) data preparation:
and performing sample selection by setting a time and space composite condition to obtain the transfer transaction data and asset use information of each bank user.
The method specifically comprises the following steps: the bank transfer transaction pipeline is the fundamental data for building the graph structure. And selecting samples by setting a composite condition of time and space. With respect to time conditions, a wider time window (e.g., three months, six months, more than one year) needs to be set to better measure the relationship between customers. Regarding the spatial condition, the condition is mainly to reduce the size of the data set and improve the efficiency of composition and calculation due to the huge bank transaction volume. Meanwhile, the region setting is also to meet the requirements of actual services.
2-2) data preprocessing:
and screening the transfer transaction data of each bank user, and reserving effective bank transfer transaction data.
The method specifically comprises the following steps: the bank transfer transaction data excluding invalid bank transfer transaction data mainly comprises that a transaction opponent is a third-party payment company, bank system batch account transfer, mutual transfer of a plurality of bank cards under the name of a client, transfer transactions to public accounts (such as private to public, public to public), incomplete transfer transactions (such as the transaction amount is 0) and the like. Data cleansing here is primarily based on rules, where a rule is a definition of invalid transactions. In addition to the above transaction examples, the selection and the combined application are not limited to the definition of other invalid samples, and are performed according to the actual situation.
2-3) node generation:
and setting the selection of the node granularity, wherein the selection comprises the step of taking the client as the node and the bank card as the node, and the granularity is determined by a service scene.
The method specifically comprises the following steps:
firstly, the selection of node granularity is carried out, wherein the granularity is determined by a service scene, and the selection comprises that a client is used as a node and a bank card is used as a node. The second is object selection, which also selects a customer population based on rules, which are any combination of conditions, and are not limited herein. For example, the area range is set. The added node attribute mainly comprises four parts: 1. user important attributes such as home conditions, work conditions, car as a house cell phone, etc.; 2. asset attributes such as deposit, financing, securities, insurance, and the like; 3. liability attributes such as small cash credits, consumer credits, house credits, etc.; 4. transacting services such as credit card, account rating, personal credit, etc.
2-4) generating a relation edge:
and evaluating the relationship between the client and the client according to the transaction behavior, and generating a relationship edge for the account transfer transaction data by adopting rules, statistics, clustering and the like.
The method specifically comprises the following steps:
definition of relationship edges: eligible transactions constitute valid relationship edges. Regarding the transaction condition setting, three ways are provided here: 1. the business gives static rules; 2. transaction behavior analysis is based primarily on transfer transaction data. Statistics are made on the transactions, including the number of transactions, frequency of transactions, amount of transactions, etc. within a given time window. And analyzing scenes, such as transaction time distribution, account behaviors before and after transaction and the like. The analysis result is used for constructing rule conditions; 3. the two methods are combined. For both parties of the transaction meeting the conditions, a relationship edge exists between the two parties.
Establishing a relation edge: for both sides of the transaction meeting the conditions, a directed relation edge is connected between the nodes on the graph to establish a graph structure. The edge attribute includes three parts: 1. the transaction behavior statistics is not limited to statistics in the aspects of transaction quantity, transaction frequency, transaction amount, mutual transaction, transaction time and the like; 2. based on the transfer transaction data and other data, the constructor is used for quantifying transaction relationships, such as transaction closeness and comprehensive intimacy; 3. if the relevant labels reflecting the customer relations exist in the several bins, the relevant labels can be used as the attribute supplement of the relation edges. Such as family or friend relationships generated from the account transfer messages.
Evaluation of relationship edges: and generating a graph structure by using the same method for the data sets in different time intervals, and counting and comparing the nodes and the relation edges of the graph. When the contact ratio of the nodes and the relation edges reaches a certain threshold value, the graph structure is stable, otherwise, the graph structure needs to be returned to the definition of the relation edges for adjustment.
3) Pruning a graph model:
and analyzing the nodes and the relation edges on the graph by adopting the technologies of statistics, clustering, abnormal value processing and the like, and deleting outlier samples which do not accord with data distribution. For example, a node with a very large degree of departure, a relationship edge with a significant anomaly in transaction amount or frequency.
With respect to step S12, it should be noted that, in the embodiment of the present invention, as shown in fig. 2, the following is specifically performed:
1) establishing a user community:
and analyzing the topological structure of the transfer transaction relationship network by adopting a community discovery algorithm, and dividing the graph into a plurality of nodes and subsets of relationship edges.
The method comprises the steps of analyzing a topological structure of a transfer transaction network by adopting a community discovery algorithm, and dividing a graph into a plurality of nodes and subsets of relational edges, wherein the community discovery algorithm comprises L PA, L ovain, Informap and the like, and is selected and applied according to actual situations.
2) User community post-processing:
when the size of the user community is larger than a certain threshold value, the user community is analyzed and divided into communities with relatively small and balanced sizes.
The method specifically comprises the following steps: when the community size is larger than a certain threshold value, the communities are analyzed and divided into relatively small and balanced communities. The subdivision may lose several relational edges, or isolate several nodes.
3) Constructing a user community portrait:
and analyzing the node attribute and the relation edge attribute of the user community by adopting a rule, statistic or clustering technology, and establishing a community label.
The method specifically comprises the following steps: the node attributes and the relationship edge attributes of the communities are analyzed by adopting the technologies such as rules, statistics or clustering, community labels are established, and the community labels are not limited to client attribute distribution (according to gender, age group, working condition, mobile phones and the like), client level distribution (according to account number level, fixed assets, mobile assets and the like), asset allocation distribution (according to financing, securities, insurance and the like), asset statistics, liability statistics, business statistics, transaction statistics and the like. And analyzing and calculating to obtain a community portrait result.
4) And (3) evaluating the influence of the nodes:
and analyzing the community, finding out the node with the maximum influence, determining the influence evaluation result of the node, and adding the node influence evaluation result into the community label.
The method comprises the following steps of 1, analyzing a community by adopting a node influence algorithm and finding a node with the largest influence, wherein the algorithm is not limited to PageRank, HITS, L eaderRank and the like, 2, customizing an influence evaluation function, quantifying the influence of the node on the community based on density related indexes (centrality, closeness and the like) of a graph structure, transaction statistics and the like, and determining leader clients in the community, and 3, combining the two modes and adding a node influence evaluation result into the community attribute.
With respect to step S13, it should be noted that, in the embodiment of the present invention, the following is specifically performed:
1) the graph model is used for accurate marketing of banks:
defining combination conditions according to business requirements, searching user communities meeting the conditions according to the combination conditions, and then carrying out product marketing measures on clients with large influence in the communities.
The method specifically comprises the following steps: defining condition combinations according to business requirements, such as financing preference, assets of 10 ten thousand yuan, intermediate-yield levels and the like, searching communities which meet or are similar according to the conditions, and then carrying out marketing measures such as product popularization on clients with large influence in the communities. The effect evaluation mode is that the product sales conditions of the clients and the clients in the community are counted in a period of time after marketing.
2) Graph model generation features as a complement to the customer label hierarchy:
and performing marketing process analysis, marketing data analysis and other related data analysis support according to the community where the client is located, the community label and the attribute of the client in the community.
The method specifically comprises the following steps: the data mainly comprises the community where the client is located, community-related attributes and attributes of the client in the community. Here, the system is mainly used for marketing process analysis, marketing data interpretation and supporting other related data work.
3) Graph model generation features learning models for bank customer marketing:
and generating features according to the graph model to form a feature sample set for establishing a learning model for marketing of bank customers.
The method specifically comprises the following steps: the features here include three parts: 1. graph attributes. The method mainly comprises the attributes of client nodes, communities in which clients are located, community-related attributes, the attributes of the clients in the communities and the like; 2. graph index. Quantifying the structure of the transfer transaction network from the connectivity, the centrality, the group degree and the like of the graph, and taking the calculation result as the characteristic; 3. a map vector. And extracting topological structure information from the transfer transaction network by adopting a graph embedding technology, and mapping the topological structure information into an embedded vector as a characteristic. The three characteristics are selected and combined according to actual conditions, and generated characteristics can be combined with existing characteristics, and can also directly form a sample set for a learning model of bank customer marketing.
The embodiment of the invention provides a bank accurate marketing method based on a graph model, which is used for establishing the graph model of fund transaction behaviors based on the relevance and the similarity of the fund transaction behaviors among bank customers, can be used for positioning the bank customer groups and recommending bank products, finds the current customer groups and customers with larger influence to popularize, and improves marketing conversion to a certain extent. In addition, the graph model generation characteristics, the community where the client is located, the community related attributes and the attributes of the client in the community can be used as a supplement of a bank client label system, so that data analysis is facilitated, and interpretability is enhanced. The graph model generation features, including graph attributes, graph indexes and graph vectors, can be combined with existing features or form a sample set, and are used for enhancing the overall effect of the learning model in a bank customer marketing scene.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (4)
1. A bank accurate marketing method based on a graph model is characterized by comprising the following steps:
constructing a graph model according to the transfer transaction data and the asset use information of each bank user;
optimizing the graph model to construct a graph model with a user community;
and carrying out bank precision marketing according to the graph model with the user community.
2. The graph model-based bank precision marketing method according to claim 1, wherein the constructing of the graph model according to the transaction data and the asset use information of each bank user comprises:
1) designing a graph model:
transfer transaction data among all bank customers are converted to form a transfer transaction relation network among the bank customers, the transfer transaction relation network takes bank cards as nodes, transfer transactions among the bank cards as relation edges, the nodes are customer nodes, and the relation edges are connection edges among the customer nodes; wherein the attributes of the client nodes are corresponding client portrait data;
2) and (3) realizing a graph model:
2-1) data preparation:
sample selection is carried out by setting composite conditions of time and space, and account transfer transaction data and asset use information of all bank users are obtained;
2-2) data preprocessing:
screening the transfer transaction data of each bank user, and reserving effective bank transfer transaction data;
2-3) node generation:
setting the selection of node granularity, wherein the selection comprises the steps of taking a customer as a node and taking a bank card as a node, and the granularity is determined by a service scene;
2-4) generating a relation edge:
evaluating the relationship between the client and the client according to the transaction behavior, and generating a relationship edge for the account transfer transaction data by adopting rules, statistics or clustering and the like;
3) pruning a graph model:
and analyzing the nodes and the relation edges on the graph by adopting the technologies of statistics, clustering, abnormal value processing and the like, and deleting outlier samples which do not accord with data distribution.
3. The graph model-based bank precision marketing method according to claim 1, wherein the optimizing the graph model to construct a graph model with a community of users comprises:
1) establishing a user community:
analyzing the topological structure of the transfer transaction relationship network by adopting a community discovery algorithm, and dividing the graph into a plurality of nodes and subsets of relationship edges;
2) user community post-processing:
when the scale of the user community is larger than a certain threshold value, analyzing the user community and dividing the user community into communities with relatively small and balanced scale;
3) constructing a user community portrait:
analyzing the node attribute and the relation edge attribute of the user community by adopting a rule, statistic or clustering technology, and establishing a community label;
4) and (3) evaluating the influence of the nodes:
and analyzing the community, finding out the node with the maximum influence, determining the influence evaluation result of the node, and adding the node influence evaluation result into the community label.
4. The graph model-based bank precision marketing method according to claim 1, wherein the bank precision marketing according to the graph model with the user community comprises:
1) the graph model is used for accurate marketing of banks:
defining combination conditions according to business requirements, searching user communities meeting the conditions according to the combination conditions, and then carrying out product marketing measures on clients with large influence in the communities;
2) graph model generation features as a complement to the customer label hierarchy:
according to the community where the client is located, the community label and the attribute of the client in the community, marketing process analysis, marketing data analysis and other related data analysis are supported;
3) graph model generation features learning models for bank customer marketing:
and generating features according to the graph model to form a feature sample set for establishing a learning model for marketing of bank customers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010201982.6A CN111428092B (en) | 2020-03-20 | 2020-03-20 | Bank accurate marketing method based on graph model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010201982.6A CN111428092B (en) | 2020-03-20 | 2020-03-20 | Bank accurate marketing method based on graph model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428092A true CN111428092A (en) | 2020-07-17 |
| CN111428092B CN111428092B (en) | 2023-05-02 |
Family
ID=71549708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010201982.6A Active CN111428092B (en) | 2020-03-20 | 2020-03-20 | Bank accurate marketing method based on graph model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428092B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112085586A (en) * | 2020-08-10 | 2020-12-15 | 北京中亦安图科技股份有限公司 | Bank credit card cash register method based on intensive subgraph |
| CN113850611A (en) * | 2021-08-02 | 2021-12-28 | 上海画龙信息科技有限公司 | Marketing task execution method and device based on response surface and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0013010D0 (en) * | 2000-05-26 | 2000-07-19 | Ncr Int Inc | Method and apparatus for predicting whether a specified event will occur after a specified trigger event has occurred |
| AU2002950261A0 (en) * | 2002-07-15 | 2002-09-12 | Peter Rowen | Software graphical interface |
| US20040210455A1 (en) * | 2003-03-05 | 2004-10-21 | Sandy Kosloff | Method and apparatus for promoting individuals and companies and marketing the goods and services of others |
| CN106779650A (en) * | 2016-12-23 | 2017-05-31 | 中山大学 | A kind of clients fund relation loop division methods based on money transfer transactions flowing water |
| JP2017201543A (en) * | 2017-06-14 | 2017-11-09 | 株式会社Ｕｂｉｃ | Data analysis system, data analysis method, data analysis program, and recording media |
| CN107832964A (en) * | 2017-11-21 | 2018-03-23 | 江苏神威云数据科技有限公司 | Bank client relation loop analysis method and system |
| CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
| CN109509040A (en) * | 2019-01-03 | 2019-03-22 | 广发证券股份有限公司 | Predict modeling method, marketing method and the device of fund potential customers |
| CN110796354A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Enterprise electric charge recovery risk portrait method and system |
| CN110888990A (en) * | 2019-11-22 | 2020-03-17 | 深圳前海微众银行股份有限公司 | Text recommendation method, device, equipment and medium |
-
2020
- 2020-03-20 CN CN202010201982.6A patent/CN111428092B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0013010D0 (en) * | 2000-05-26 | 2000-07-19 | Ncr Int Inc | Method and apparatus for predicting whether a specified event will occur after a specified trigger event has occurred |
| AU2002950261A0 (en) * | 2002-07-15 | 2002-09-12 | Peter Rowen | Software graphical interface |
| US20040210455A1 (en) * | 2003-03-05 | 2004-10-21 | Sandy Kosloff | Method and apparatus for promoting individuals and companies and marketing the goods and services of others |
| CN106779650A (en) * | 2016-12-23 | 2017-05-31 | 中山大学 | A kind of clients fund relation loop division methods based on money transfer transactions flowing water |
| JP2017201543A (en) * | 2017-06-14 | 2017-11-09 | 株式会社Ｕｂｉｃ | Data analysis system, data analysis method, data analysis program, and recording media |
| CN107832964A (en) * | 2017-11-21 | 2018-03-23 | 江苏神威云数据科技有限公司 | Bank client relation loop analysis method and system |
| CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
| CN109509040A (en) * | 2019-01-03 | 2019-03-22 | 广发证券股份有限公司 | Predict modeling method, marketing method and the device of fund potential customers |
| CN110796354A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Enterprise electric charge recovery risk portrait method and system |
| CN110888990A (en) * | 2019-11-22 | 2020-03-17 | 深圳前海微众银行股份有限公司 | Text recommendation method, device, equipment and medium |
Non-Patent Citations (2)
| Title |
|---|
| SUMAN ROY: "《An Empirical Study of Error Patterns in Industrial Business Process Models》" * |
| 杨晓龙: "《银行客户精确营销系统设计与实现》" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112085586A (en) * | 2020-08-10 | 2020-12-15 | 北京中亦安图科技股份有限公司 | Bank credit card cash register method based on intensive subgraph |
| CN112085586B (en) * | 2020-08-10 | 2024-04-16 | 北京中亦安图科技股份有限公司 | Bank credit card anti-cash registering method based on dense subgraph |
| CN113850611A (en) * | 2021-08-02 | 2021-12-28 | 上海画龙信息科技有限公司 | Marketing task execution method and device based on response surface and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428092B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wen et al. | Customer purchase behavior prediction from payment datasets | |
| Bose et al. | Exploring business opportunities from mobile services data of customers: An inter-cluster analysis approach | |
| WO2011112981A2 (en) | Methods, computer-accessible medium and systems for construction of and inference with networked data, for example, in a financial setting | |
| CN104321794A (en) | A system and method using multi-dimensional rating to determine an entity's future commercial viability | |
| CN111428092B (en) | Bank accurate marketing method based on graph model | |
| CN113781139A (en) | Item recommendation method, item recommendation device, equipment and medium | |
| Firdaus et al. | development of bank’s customer segmentation model based on rfm+ b approach | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN116401379A (en) | Financial product data pushing method, device, equipment and storage medium | |
| Khder et al. | The impact of implementing data mining in business intelligence | |
| Melian et al. | Customer churn prediction in telecommunication industry. A data analysis techniques approach | |
| Hsieh et al. | Enhancing consumer behavior analysis by data mining techniques | |
| Shashidhar et al. | Customer segmentation of bank based on data mining–security value based heuristic approach as a replacement to K-means segmentation | |
| CN112950359A (en) | User identification method and device | |
| Droftina et al. | A diffusion model for churn prediction based on sociometric theory | |
| CN112085332A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113870021B (en) | Data analysis method and device, storage medium and electronic equipment | |
| Fraihat et al. | An efficient enhanced k-means clustering algorithm for best offer prediction in telecom | |
| CN114565450A (en) | Overdue common debt-based collection strategy determination method and related equipment | |
| CN114331665A (en) | Training method and device for credit judgment model of predetermined applicant and electronic equipment | |
| CN113256351A (en) | User service demand identification method and device and computer readable storage medium | |
| CN109919811B (en) | Insurance agent culture scheme generation method based on big data and related equipment | |
| CN115147117A (en) | Method, device and equipment for identifying account group with abnormal resource use | |
| Granov | Customer loyalty, return and churn prediction through machine learning methods: for a Swedish fashion and e-commerce company | |
| Olson et al. | Data mining process |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |