Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system for predicting user loss of e-commerce website

An e-commerce website and prediction method technology, applied in the field of user loss prediction, can solve problems such as user loss, failure to take timely countermeasures, and inability to predict the probability of user loss, so as to improve loyalty, improve product display methods, and increase product quality. benefit effect

Inactive Publication Date: 2018-01-09
CTRIP COMP TECH SHANGHAI
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the defect that the analysis method of user churn in the prior art has a delay in predicting user churn, and cannot predict the real-time churn probability of users, resulting in the inability to take countermeasures in time, resulting in the real loss of users. Method and system for predicting user loss of e-commerce website

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
  • Method and system for predicting user loss of e-commerce website
  • Method and system for predicting user loss of e-commerce website
  • Method and system for predicting user loss of e-commerce website

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1As shown, the method for predicting the loss of users of the e-commerce website of the present embodiment includes the following steps:

[0055] Step 101. Obtain historical related data of multiple users, and divide the historical related data into first training data and first test data according to a set ratio.

[0056] Wherein, the user to which the test data belongs is the test user. When a user logs in, the historical related data of the test user and other users can be called from the database as a sample.

[0057] Step 102, extracting first feature data from the first training data, and establishing a first prediction model based on the first feature data.

[0058] Wherein, the first feature data may be: the user's historical browsing information, historical order information, comment information, and the like. That is to say, the first prediction model uses multiple feature dimensions to represent the user's historical order probability, and t...

Embodiment 2

[0104] Such as image 3 As shown, the system for predicting user churn of an e-commerce website in this embodiment includes: a data acquisition module 1 , a model building module 2 and a calculation module 3 .

[0105] The data acquisition module 1 is used to acquire historical related data of multiple users, and divide the historical related data into first training data and first test data according to a set ratio.

[0106] The model building module 2 is used to extract first feature data from the first training data, and build a first prediction model based on the first feature data. Wherein, the first prediction model uses multiple feature dimensions to represent the user's historical order probability. Wherein, the first feature data includes at least one of the following parameters: historical browsing information, historical order information and comment information.

[0107] The calculation module 3 is used to extract the first feature data from the first test data, ...

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 method and system for predicting user loss of an e-commerce website. The method includes dividing obtained historical related data of a plurality of users into first trainingdata and first test data; establishing a first prediction model according to first characteristic data in the first training data; inputting the first characteristic data in the first test data to the first prediction model to calculate historical order-placing probabilities of users; dividing obtained current operation data of a plurality of users into second training data and second test data;establishing a second prediction model according to second characteristic data in the second training data; inputting the second characteristic data in the second test data to the second prediction model to calculate current order-placing probabilities of users; and calculating loss probabilities of tested users. The method for predicting user loss of an e-commerce website can quantify the real-time loss probabilities of users, so as to provide reference for product display of a supplier.

Description

technical field [0001] The invention relates to the technical field of e-commerce, in particular to a method and system for predicting user loss of an e-commerce website. Background technique [0002] With the rapid development of e-commerce sites, such as OTA (Online Travel Agent, online travel agency) industry, the competition among OTAs is becoming increasingly fierce, and the ways for users to choose hotels online are more extensive; on the other hand, the continuous improvement of hotel revenue management , The hotel itself is also constantly digging potential loyal users, which has led to the increasing loss of users of e-commerce websites. For any Internet product, the loss of users will directly affect the revenue of a product; and the loss of users reflects that the needs of users are not met, and there is room for improvement in the services provided by the product. User churn has always been a research hotspot in academia and industry. The problem of user churn i...

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): G06Q30/02
Inventor 刘金勇陈毅鸿江文谢文丹
Owner CTRIP COMP TECH SHANGHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com