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

A CTR Prediction Method Based on Cost-Sensitive Classifier Ensemble

A cost-sensitive, ad click-through technology, applied in forecasting, instrumentation, genetic rules, etc., can solve the problems of less feature dimensions, insufficient data preprocessing, and low accuracy, so as to achieve improved accuracy, good learning features, and high applicability sexual effect

Active Publication Date: 2022-03-29
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the deficiencies of the prior art, and propose a method for predicting the click-through rate of advertisements based on the integration of cost-sensitive classifiers, which solves the problems of some current click-through rate forecasting algorithms due to fewer feature dimensions and insufficient data preprocessing. This method can better improve the accuracy of advertising click-through rate 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
  • A CTR Prediction Method Based on Cost-Sensitive Classifier Ensemble
  • A CTR Prediction Method Based on Cost-Sensitive Classifier Ensemble
  • A CTR Prediction Method Based on Cost-Sensitive Classifier Ensemble

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to describe the present invention more specifically, the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0046] In this example, we apply a cost-sensitive classifier ensemble-based advertising click-through rate prediction method to the advertising dataset. Such as figure 1As shown, the method mainly includes the following steps:

[0047] First, feature extraction and sampling are performed on user behavior history records, and a sample set including user information, advertisement information, user click logs, user historical purchase behavior and other information is obtained from it; for this implementation For example, since the dataset comes from real data, preprocessing is required to remove some abnormal data. For example, high-click zero-purchase users who are suspected of crawling, advertisements and products with missing key information, etc. The...

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 for predicting the click-through rate of advertisements based on the integration of cost-sensitive classifiers. The improved B-SMOTE+ method is used for data oversampling in the rate prediction; the data set after data preprocessing is passed to the classifier for learning, and the cost-sensitive algorithm is used to increase the punishment for the mistake of "clicking on the advertisement"; The genetic algorithm is used to optimize the parameters; the two-layer Stacking method is used to integrate. The present invention solves the problems of low accuracy rate of some current click-through rate prediction algorithms due to fewer feature dimensions, inadequate data preprocessing and the like, and adopts the method to better improve the accuracy rate of advertisement click-through rate prediction.

Description

technical field [0001] The invention relates to the technical field of electronic recommendation algorithms, in particular to an advertisement click-through rate prediction method based on cost-sensitive classifier integration. Background technique [0002] Predicting the click-through rate of advertisements can select the advertisement with a higher click-through rate for precise targeting by calculating the click-through rate of a certain type of advertisement for a specific user based on a given user and web page content. Adopting this mechanism can greatly increase the click-through rate of advertisements placed by advertisers, increase the number of visits to products placed in advertisements, and help users obtain high-quality information. Click-through rate prediction is an urgent problem that is widely used in the Internet field. It also includes the ranking results of search engines and recommendation systems, and the click-through rate of advertisements is an impor...

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 Patents(China)
IPC IPC(8): G06Q30/02G06Q10/04G06N3/12G06K9/62
CPCG06N3/126G06Q10/04G06Q30/0242G06F18/2411
Inventor 王昊翔林启迪张星明林育蓓
Owner SOUTH CHINA UNIV OF TECH
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