CN113065946A - Classification updating promoting method and device for overdue credit card certificate clients and storage medium - Google Patents
Classification updating promoting method and device for overdue credit card certificate clients and storage medium Download PDFInfo
- Publication number
- CN113065946A CN113065946A CN202110285428.5A CN202110285428A CN113065946A CN 113065946 A CN113065946 A CN 113065946A CN 202110285428 A CN202110285428 A CN 202110285428A CN 113065946 A CN113065946 A CN 113065946A
- Authority
- CN
- China
- Prior art keywords
- update
- intention
- credit card
- clients
- updated
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/23—Updating
- G06F16/2379—Updates performed during online database operations; commit processing
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to a method, a device and a storage medium for prompting updating of classified customers when credit card certificates are expired. The method comprises the following steps: s1, constructing a data warehouse and collecting user data of credit card users; s2, selecting positive and negative samples to form a training set by combining the clients which are successfully updated and the clients which are not updated based on the credit card user data; s3, constructing an updating will prediction model, and training the model based on a training set; s4, for the clients to be classified and promoted to be updated, predicting update intention levels of the clients based on user data by using a trained update intention prediction model; and S5, matching an update promoting scheme based on the update intention level. Compared with the prior art, the method and the device can accurately and reliably obtain the update intention level and match the update promotion scheme, thereby greatly improving the update promotion rate.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a classified updating promoting method for clients with expired credit card certificates.
Background
The personal certificate information filled by a credit card holding client in the process of transacting the card opening business has timeliness, and according to the supervision specification of China people's banks, after the validity period of the client certificate is over, the credit card under the client name can be controlled within a reasonable updating time range, so that the client cannot continue to use the card, inconvenience is brought to the client, and meanwhile, the risk of client loss is brought to the banks. One of the existing solutions is to regularly and periodically remind a client regularly according to legal compliance so as to activate the client to update the certificate validity period; and the other method is to select part of the clients from the group of clients to perform activity prompt updating and reward the clients with the certificate updating reaching the standard in the activity.
The current method has the following two pain points:
1) the certificate update rate is low and reaches the bottleneck. The renewal rate of the monthly certificate expired clients is lower than the growth rate of the certificate expired clients, so that the certificate expired integral customer group is accumulated continuously, and the quality of the customer group sinks along with the change of time;
2) the two updating promoting modes of activity promotion and conventional reminding are not combined with each other, so that experience cannot be shared, and an overall operation scheme is lacked.
Disclosure of Invention
The present invention is directed to a method, an apparatus and a storage medium for facilitating update of customer classification when a credit card is expired.
The purpose of the invention can be realized by the following technical scheme:
a credit card certificate expired customer classification update promoting method comprises the following steps:
s1, constructing a data warehouse and collecting user data of credit card users;
s2, selecting positive and negative samples to form a training set by combining the clients which are successfully updated and the clients which are not updated based on the credit card user data;
s3, constructing an updating will prediction model, and training the model based on a training set;
s4, for the clients to be classified and promoted to be updated, predicting update intention levels of the clients based on user data by using a trained update intention prediction model;
and S5, matching an update promoting scheme based on the update intention level.
Preferably, the data warehouse adopts an HDFS distributed file storage mode.
Preferably, the user data comprises basic information before credit, card data used in credit, channel behavior number in credit and payment collection data after credit.
Preferably, the update will prediction model includes a lightGBM model.
Preferably, the update intention levels output by the update intention prediction model include at least three types, which are respectively: the client group is updated with high intention, the client group is updated with medium intention, and the client group is updated with low intention.
Preferably, the method further comprises the steps of expanding the training set and regularly retraining the optimization intention prediction model.
Preferably, the step S5 matches the update facilitation schemes by using a pre-stored update facilitation willingness-scheme matching table, which corresponds each type of update facilitation level to one or more update facilitation schemes.
Preferably, the update-promoting will-scheme matching table is obtained by an AB test theory.
A credit card certificate expired customer classification updating promoting device comprises a memory and a processor; the memory for storing a computer program; the processor is used for realizing the customer classification update promoting method when the credit card certificates are expired when the computer program is executed.
A storage medium having stored thereon a computer program which, when executed by a processor, implements the method for facilitating renewal of a credit card instrument expired customer classification.
Compared with the prior art, the invention has the following advantages:
(1) the invention predicts the update intention level of the overdue credit card evidence client by using the machine learning model based on the user data, thereby matching the update promotion scheme, and the method is more objective and reliable;
(2) according to the invention, an optimal update promotion scheme can be found through the classification of the update will grades, and the update rate can be continuously improved.
Drawings
FIG. 1 is a block diagram illustrating a method for facilitating update of customer classification when a credit card certificate is expired according to the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. Note that the following description of the embodiments is merely a substantial example, and the present invention is not intended to be limited to the application or the use thereof, and is not limited to the following embodiments.
Example 1
As shown in fig. 1, the present embodiment provides a method for facilitating update of customer classification when a credit card certificate expires, which includes the following steps:
s1, constructing a data warehouse and collecting user data of credit card users;
the data warehouse adopts an HDFS distributed file storage mode.
The user data comprises basic information before credit, card data used in credit, channel behavior data in credit and payment collection data after credit. The basic information before the credit includes gender, age, academic calendar and the like, the card data used in the credit includes consumption amount of nearly 1 month, consumption amount of nearly 3 months and consumption category, the channel behavior data in the credit includes the number and category of customer service incoming lines, the number and category of clicks of WeChat public numbers, the number and stay time of APP login clicks, and the data of payment and collection after the credit includes payment data.
And S2, selecting positive and negative samples to form a training set by combining the clients with successful update and the clients without update based on the credit card user data.
S3, establishing an updating intention prediction model, and performing model training based on the training set, wherein the updating intention prediction model comprises a lightGBM model. The update intention levels output by the update intention prediction model comprise at least three types, namely: the client group is updated with high intention, the client group is updated with medium intention, and the client group is updated with low intention.
S4, for the clients to be classified and promoted to be updated, predicting update intention levels of the clients based on user data by using a trained update intention prediction model;
and S5, matching an update promoting scheme based on the update intention level. The matching update promoting scheme is obtained through a pre-stored update promoting willingness-scheme matching table, and each type of update promoting willingness level corresponds to one or more update promoting schemes through the update promoting willingness-scheme matching table. And the update promotion will-scheme matching table is obtained through an AB test theory. Respectively selecting part of customers from the three classes of customer groups, and setting a plurality of activity variables to perform an AB test comparison experiment; according to the AB test theory, partial guests are respectively selected for three classes of guests, about 10 thousands of guests are respectively selected for each class of guests, activity variables such as promotion dialects (strict dialects and warm dialects), credit card lines (first-class reward lines, second-class reward lines and third-class reward lines) and the like are constructed, an experiment group and a comparison group are set according to different strategies, AB test comparison promotion experiments are carried out, and therefore one or more corresponding promotion updating schemes under each class of updating wish level are obtained.
The method further comprises the steps of expanding the training set and regularly retraining the optimization intention prediction model. In this way, the cyclic iteration is carried out for multiple times, the update rate of the whole passenger group can be gradually improved, and the upper limit of the update rate is continuously approached. And the new data and the original data are used for continuing parameter training or a neural network algorithm is introduced, so that the algorithm classification is more accurate, and the passenger group strategies of all classes are more differentiated. And returning to the step 1 to iteratively actuate updating, and continuously increasing the overall updating rate by the loop.
Example 2
The embodiment provides a credit card certificate expired customer classification updating promoting device, which comprises a memory and a processor; the memory for storing a computer program; the processor is configured to implement the method for facilitating update of customer classification when the credit card certificate expires as described in embodiment 1 when executing the computer program, and the method is the same as embodiment 1 and is not described herein again.
Example 3
This embodiment provides a storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for facilitating update of a class of customer when a credit card certificate expires as described in embodiment 1, and the method is the same as embodiment 1 and will not be described herein again.
The above embodiments are merely examples and do not limit the scope of the present invention. These embodiments may be implemented in other various manners, and various omissions, substitutions, and changes may be made without departing from the technical spirit of the present invention.
Claims (10)
1. A credit card certificate expired customer classification update promoting method is characterized by comprising the following steps:
s1, constructing a data warehouse and collecting user data of credit card users;
s2, selecting positive and negative samples to form a training set by combining the clients which are successfully updated and the clients which are not updated based on the credit card user data;
s3, constructing an updating will prediction model, and training the model based on a training set;
s4, for the clients to be classified and promoted to be updated, predicting update intention levels of the clients based on user data by using a trained update intention prediction model;
and S5, matching an update promoting scheme based on the update intention level.
2. The method as claimed in claim 1, wherein the data warehouse employs HDFS distributed file storage mode.
3. The method as claimed in claim 1, wherein the user data includes basic information before credit, card data during credit, channel behavior number during credit and payment collection data after credit.
4. The method as claimed in claim 1, wherein the forecast model comprises a lightGBM model.
5. The method as claimed in claim 1, wherein the update intention prediction model outputs update intention levels including at least three categories, respectively: the client group is updated with high intention, the client group is updated with medium intention, and the client group is updated with low intention.
6. The method as claimed in claim 1, further comprising expanding the training set and retraining the optimization intention prediction model periodically.
7. The method as claimed in claim 1, wherein the step S5 is performed by using a pre-stored update willingness-to-scheme matching table, wherein the update willingness-to-scheme matching table associates each update willingness level with one or more update schemes.
8. The method as claimed in claim 7, wherein the update willingness-scheme matching table is obtained by AB test theory.
9. A credit card certificate expired customer classification updating promoting device is characterized by comprising a memory and a processor; the memory for storing a computer program; the processor, when executing the computer program, is configured to implement the method for facilitating update of the customer classification when the credit card certificate expires according to any one of claims 1 to 8.
10. A storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method for facilitating update of a class of customers for expiring credit card certificates according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110285428.5A CN113065946A (en) | 2021-03-17 | 2021-03-17 | Classification updating promoting method and device for overdue credit card certificate clients and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110285428.5A CN113065946A (en) | 2021-03-17 | 2021-03-17 | Classification updating promoting method and device for overdue credit card certificate clients and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113065946A true CN113065946A (en) | 2021-07-02 |
Family
ID=76561189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110285428.5A Pending CN113065946A (en) | 2021-03-17 | 2021-03-17 | Classification updating promoting method and device for overdue credit card certificate clients and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065946A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633326A (en) * | 2017-09-14 | 2018-01-26 | 北京拉勾科技有限公司 | A kind of user delivers the construction method and computing device of wish model |
| CN109815489A (en) * | 2019-01-02 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Collection information generating method, device, computer equipment and storage medium |
| CN110348727A (en) * | 2019-07-02 | 2019-10-18 | 北京淇瑀信息科技有限公司 | A kind of marketing strategy formulating method, device and electronic equipment moving branch wish based on consumer's risk grade and user |
| CN110363650A (en) * | 2019-06-27 | 2019-10-22 | 上海淇毓信息科技有限公司 | A kind of storage user dynamic branch wish prediction technique, device and system |
| CN111145009A (en) * | 2019-12-12 | 2020-05-12 | 北京淇瑀信息科技有限公司 | Method and device for evaluating risk after user loan and electronic equipment |
| CN111192136A (en) * | 2019-12-24 | 2020-05-22 | 中信百信银行股份有限公司 | Credit service collection method and device, electronic equipment and storage medium |
| CN112131479A (en) * | 2020-09-30 | 2020-12-25 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and storage medium |
| CN112328869A (en) * | 2020-09-28 | 2021-02-05 | 苏宁金融科技(南京)有限公司 | User loan willingness prediction method and device and computer system |
-
2021
- 2021-03-17 CN CN202110285428.5A patent/CN113065946A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633326A (en) * | 2017-09-14 | 2018-01-26 | 北京拉勾科技有限公司 | A kind of user delivers the construction method and computing device of wish model |
| CN109815489A (en) * | 2019-01-02 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Collection information generating method, device, computer equipment and storage medium |
| CN110363650A (en) * | 2019-06-27 | 2019-10-22 | 上海淇毓信息科技有限公司 | A kind of storage user dynamic branch wish prediction technique, device and system |
| CN110348727A (en) * | 2019-07-02 | 2019-10-18 | 北京淇瑀信息科技有限公司 | A kind of marketing strategy formulating method, device and electronic equipment moving branch wish based on consumer's risk grade and user |
| CN111145009A (en) * | 2019-12-12 | 2020-05-12 | 北京淇瑀信息科技有限公司 | Method and device for evaluating risk after user loan and electronic equipment |
| CN111192136A (en) * | 2019-12-24 | 2020-05-22 | 中信百信银行股份有限公司 | Credit service collection method and device, electronic equipment and storage medium |
| CN112328869A (en) * | 2020-09-28 | 2021-02-05 | 苏宁金融科技(南京)有限公司 | User loan willingness prediction method and device and computer system |
| CN112131479A (en) * | 2020-09-30 | 2020-12-25 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112381428B (en) | Service distribution method, device, equipment and storage medium based on reinforcement learning | |
| US20190213522A1 (en) | System and method for determining user metrics | |
| CN107239928B (en) | The flow generation method and device of a kind of resource allocation | |
| US11995715B1 (en) | Capital loan optimization | |
| McFowland III et al. | A prescriptive analytics framework for optimal policy deployment using heterogeneous treatment effects. | |
| Luo et al. | Are recoveries all the same: GDP and TFP? | |
| US20230259937A1 (en) | Authentication Question Topic Exclusion Based on Response Hesitation | |
| Lahoz et al. | A multi-objective micro genetic ELM algorithm | |
| Kendall et al. | On the complexity of forming mental models | |
| Yancey et al. | A sleeping, recovering bandit algorithm for optimizing recurring notifications | |
| CN114066622A (en) | Small and micro enterprise credit rating method and device | |
| CN113065946A (en) | Classification updating promoting method and device for overdue credit card certificate clients and storage medium | |
| CN111882113B (en) | Enterprise mobile banking user prediction method and device | |
| EP3764310A1 (en) | Prediction task assistance device and prediction task assistance method | |
| CN116645134A (en) | Method, device, equipment and medium for recommending credit card in stages | |
| CN110059457B (en) | Body-building method and device | |
| CN113393320B (en) | Enterprise financial service risk prediction method and device | |
| CN116401355A (en) | Consultation business decision management method and system based on digital intelligence interaction | |
| CN115719183A (en) | Power customer self-feedback service evaluation method and system based on weight dynamic grading | |
| CN114004307A (en) | Tariff package depreciation user prediction method based on user data | |
| CN110930237B (en) | SAGDO algorithm-based small and medium-sized enterprise credit prediction classification method | |
| CN113407827A (en) | Information recommendation method, device, equipment and medium based on user value classification | |
| Hadden | A customer profiling methodology for churn prediction | |
| CN110931113A (en) | Hospital management operation system and method based on Internet cloud platform | |
| CN117094536B (en) | Order data analysis method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210702 |