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

Enterprise information loss prediction method of double-layer structure

A two-layer structure and prediction method technology, applied in the field of data processing, can solve the problems of low accuracy and precision, achieve the effect of improving accuracy and precision, and improving the customer churn prediction model

Pending Publication Date: 2020-06-05
杭州策知通科技有限公司
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a two-layer structure enterprise information loss prediction method, which aims to solve the problems of low accuracy and precision in the prior art

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
  • Enterprise information loss prediction method of double-layer structure
  • Enterprise information loss prediction method of double-layer structure
  • Enterprise information loss prediction method of double-layer structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 As shown, a two-tier structure enterprise intelligence loss prediction method includes the following steps:

[0059] S110. Obtain a data set, and divide the data set into a training set and a test set;

[0060] S120. Using XGBoost, LightGBM, AdaBoost and a weighted voting algorithm, perform two-layer training on the training set, and output the evaluation index of the classification prediction model;

[0061] S130. Analyzing and comparing the results of the evaluation index of the classification prediction model with the comparison object.

[0062] According to Embodiment 1, the system obtains a data set, divides the data set into a training set and a test set, and then uses XGBoost, LightGBM, AdaBoost and weighted voting algorithms to perform two-layer training on the training set, and outputs the evaluation of the classification prediction model Index, and finally analyze and compare the evaluation index of the classification prediction model with t...

Embodiment 2

[0064] Such as figure 2 As shown, a two-tier structure enterprise intelligence loss prediction method, including:

[0065] S210. Obtain a data set, and divide the data set into a training set and a test set;

[0066] S220, building a two-layer structure of the classification prediction model, the first layer trains the data set through a corresponding algorithm, and obtains the first layer data set;

[0067] S230, the second layer trains the first layer data set through the corresponding algorithm to obtain the evaluation index of the classification prediction model, wherein the calculation formula of the strong classifier in the AdaBoost algorithm is as follows:

[0068]

[0069] where x is the input vector, F(x) is the strong classifier, f t (x) is a weak classifier, α t is the weight value of the weak classifier, which is a positive number, and T is the number of weak classifiers. The output value of the weak classifier is +1 or -1, corresponding to positive and neg...

Embodiment 3

[0078] Such as image 3 As shown, a two-tier structure enterprise intelligence loss prediction method, including:

[0079] S310. Obtain a data set, and divide the data set into a training set and a test set;

[0080] S320. Using XGBoost, LightGBM, AdaBoost and a weighted voting algorithm, perform two-layer training on the training set, and output the evaluation index of the classification prediction model;

[0081] S330. Calculate the evaluation index of the comparison object;

[0082] S340. Compare the evaluation index of the classification prediction model with the evaluation index of the comparison object, and analyze and compare the results;

[0083] The calculation of the evaluation index of the comparison object mentioned in Embodiment 3 is only exemplary, and is not a limitation to the calculation of the evaluation index of the comparison object. Calculate the evaluation indicators of MLP, MLP with autoencoder fusion, MLP with entity embedding fusion, KNN, LogisticRe...

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 an enterprise information loss prediction method of a double-layer structure. The method comprises the steps: enabling a system to obtain a data set, and dividing the data setinto a training set and a test set; performing double-layer training on the training set by utilizing XGBoost, LightGBM, AdaBoost and a weighted voting algorithm, outputting evaluation indexes of a classification prediction model, and finally performing result analysis and comparison on the evaluation indexes of the classification prediction model and a comparison object. By using a double-layer fusion method and an adaptive algorithm, the accuracy and precision of the customer loss prediction model are improved, and the customer loss prediction model is further perfected.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a two-layer structure enterprise information loss prediction method. Background technique [0002] Today, various markets are becoming increasingly saturated and competitive, and the market share of industry giants is increasing. Entrepreneurs in various industries used to focus on launching novel customized services to attract new customers and convert existing customers. Convert into loyal customers. Studies have shown that the cost of developing a new customer is much higher than the cost of maintaining an old customer, so preventing the loss of old customers is a problem that entrepreneurs must pay attention to. [0003] Therefore, customer churn prediction technology is very important for enterprises to retain old customers and launch various customized services. For example, for a telecom company, if a lost customer no longer uses the service provided by the operator, he wi...

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
IPC IPC(8): G06Q10/04G06K9/62G06Q10/06
CPCG06Q10/04G06Q10/06393G06F18/214G06F18/25G06F18/241
Inventor 陈海峰杨冬豪
Owner 杭州策知通科技有限公司
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