Click rate predicting method and system based on multistage logistic regression

A technology of logistic regression and forecasting method, applied in forecasting, marketing, advertising, etc., can solve the problems of large amount of data, reduce the amount of calculation, and inaccurate forecasting, and achieve the effect of improving accuracy and efficiency

Inactive Publication Date: 2014-04-30
北京集奥聚合网络技术有限公司
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a method and system for predicting click-through rate based on multi-level logistic regression. Through multi-level logistic regression, under the premise that the dimensions remain unchanged and the number of samples remains unchanged, the amount of calculation is reduced to solve the problem of current click-through rate prediction. The problem of large amount of data and inaccurate prediction

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
  • Click rate predicting method and system based on multistage logistic regression
  • Click rate predicting method and system based on multistage logistic regression
  • Click rate predicting method and system based on multistage logistic regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0017] Such as figure 1 As shown, the method for predicting click-through rate based on multilevel logistic regression in the embodiment of the present invention mainly includes the following steps:

[0018] The feature extraction step, by analyzing the obtained click-through rate data, analyzes the factors that have an impact on the click-through rate, selects feature vectors therefrom, and constructs a feature model;

[0019] In the model training step, a multi-level logistic regression model is used to perform multi-level logistic regression machine learning on the feature model to obtain a prediction model; and

[0020] CTR prediction step: use the prediction model to predict the CTR data to be predicted.

[0021] Among them, there are many factors that affect the click-through rate, the most important ones include: advertising, media, and audience. The present invention preferably uses the following model to construct the click-through rate feature model:

[0022] μ(a,...

Embodiment 2

[0036] The click-through rate prediction system based on multilevel logistic regression in the embodiment of the present invention mainly includes as follows:

[0037] The feature extraction device is used to analyze the obtained click-through rate data, analyze factors that have an impact on the click-through rate, select feature vectors therefrom, and construct a feature model;

[0038] The model training device is used to use the multi-level logistic regression model to perform multi-level logistic regression machine learning on the feature model to obtain a prediction model; and

[0039] CTR prediction device: use the prediction model to predict the CTR data to be predicted.

[0040] Among them, there are many factors that affect the click-through rate, the most important ones include: advertising, media, and audience. The present invention preferably uses the following model to construct the click-through rate feature model:

[0041] μ(a,u,c)=p(click|a,u,c)

[0042] Am...

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 click rate predicting method and system based on multistage logistic regression. The method includes: analyzing obtained click rate data, analyzing factors affecting click rate, and selecting feature vectors in the factors to build feature models; using multistage logistic regression models to perform machine learning on the feature models to obtain prediction models; using the prediction models to predict the to-be-predicted click rate data. The method has the advantages that by multistage logistic regression, calculation amount can be reduced and calculation speed can be increased while dimensionality and sample number are unchanged, and the problem that the current click rate prediction is large in data amount and inaccurate in prediction.

Description

technical field [0001] The invention relates to the field of Internet big data machine learning processing, in particular to a method and system for predicting click rate based on multilevel logistic regression. Background technique [0002] With the improvement of global informatization, Internet applications are becoming more and more popular. Compared with traditional media advertisements, Internet advertisements account for an increasing proportion. In recent years, with the rise of online games and e-commerce and the development of online alliances that emphasize long-tail traffic, advertisers have attracted more and more attention to the actual effect of online advertising. By statistically calculating the click-through rate of advertising links, we can understand the advertisements that different users are interested in, so as to display the corresponding advertisements to each user more accurately, so as to increase the click-through rate of advertisements, improve t...

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): G06F17/30
CPCG06Q10/04G06Q30/0242G06Q30/0277
Inventor 崔晶晶林佳婕李春华受春柏刘立娜
Owner 北京集奥聚合网络技术有限公司
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap