Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Customer loss prediction method and device and storage medium

A technology of customer churn and prediction method, which is applied in the field of data processing, can solve problems such as low accuracy and retention of customers by business personnel, and achieve the effects of reducing customer churn, improving prediction accuracy, and enriching types

Active Publication Date: 2020-02-25
AGRICULTURAL BANK OF CHINA
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In this regard, the existing technology proposes to predict the customer loss situation, so that the enterprise can formulate corresponding strategies in advance and retain the old customers who may lose, but , the prediction results of the currently trained customer churn prediction model (that is, the probability of customer churn) are relatively low in accuracy, and cannot reliably help business personnel to retain real lost customers

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Customer loss prediction method and device and storage medium
  • Customer loss prediction method and device and storage medium
  • Customer loss prediction method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] This application analyzes the acquisition method of the existing customer churn prediction model. Although the existing technology proposes to train different customer churn prediction models for different types of customers, the current classification of customers is usually achieved by using a clustering algorithm. , or simply divide customers into ordinary customers and VIP customers, the former cannot realize the classification of unknown customers, and the latter classification method is too simple. There is a large gap in categories, and this classification method is not applicable to bank customers. Therefore, in order to improve the customer classification method, this application proposes to subdivide bank customers by combining services and clustering algorithms. For the specific classification method, please refer to the description in the corresponding part of the following embodiments.

[0062] In addition, for the definition of customer churn rules, for ga...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a customer loss prediction method and device and computer equipment. In a process of obtaining a customer loss prediction model, the clients are classified according to the virtual resource balance of the preset service to obtain a plurality of client bases which are more refined and reflect personal preferences of clients in the preset service; then, aiming at each customer group, original feature data of multiple dimensions of a corresponding client in a preset historical time periodand derived characteristic data of multiple dimensions are processed to obtain a modeltraining sample of the customer group; the types of model training samples are greatly enriched; thus, the model training samples are trained by using a machine learning algorithm, the prediction accuracy of the customer loss model obtained by training is greatly improved, and then the service personnel can accurately and timely know the possible lost customer list in advance according to the prediction accuracy, save the customers by adopting appropriate policies, and reduce the customer loss amount.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a customer churn prediction method, device, system and storage medium. Background technique [0002] In today's fierce market competition environment, companies often need to spend a lot of energy to develop new customers. According to statistics, it takes nearly 6 times more time to develop a new customer than to maintain an old customer. At the same time, the company The success rate of recommending products or services to existing customers is about 50%, while the success rate of recommending products or services to new customers is only 15%. It can be seen that it is very important for enterprises to maintain good existing customer relationships and avoid customer loss. [0003] In this regard, the existing technology proposes to predict the customer churn situation, so that the enterprise can formulate corresponding strategies in advance to retain the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q30/02G06K9/62G06N20/00
CPCG06Q10/04G06Q30/0201G06N20/00G06F18/23G06F18/24
Inventor 赵维平赵存超李现伟吴正良
Owner AGRICULTURAL BANK OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products