Advertisement conversion rate estimation method based on time information integration model

A technology that integrates models and time information, applied in the computer field, can solve problems such as increased training time, reduced data volume, and reduced model effects, and achieves the effects of accelerating training and improving model accuracy

Active Publication Date: 2018-05-29
SUZHOU UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The improvement of the model effect brought about by the growth of historical data is far from being able to balance the cost of increased training time brought about by the growth of historical data. However, if this part of historical data with a long time interval is directly discarded, the amount of data will be reduced and the effect of the model will be reduced. Advertisement conversion rate estimation algorithm does not maximize the value of historical data

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
  • Advertisement conversion rate estimation method based on time information integration model
  • Advertisement conversion rate estimation method based on time information integration model
  • Advertisement conversion rate estimation method based on time information integration model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0032] An advertising conversion rate estimation method based on a time information integration model, including:

[0033] Divide the advertising historical data into no less than 3 data sets according to fixed time intervals, the latest two time interval data are used as training set and test set, and the remaining time interval data are used for the training of time feature model; among them, the time feature model Use the Bagging parallel ensemble learning method in ensemble learning;

[0034] Use the rest of the time interval data as the result of the training output of the time feature model ...

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 relates to an integration learning method for increasing a conversion rate effect in a historical data timeline. Historical data is segmented according to a fixed time interval. For thehistorical data in each time interval, a plurality of uncorrelated models with different structures are trained to carry out model integration. An above integration model result is taken as a new characteristic and the new characteristic is added into time interval data which is nearest to a prediction target. Integration learning model training of the second time is performed. Because of divisionindependence among the time interval data and independence of an internal model of each time interval time data, calculating resources can be fully used to carry out parallel calculation; the data isfully used and simultaneously training time is greatly shortened; and real-time model updating can be conveniently performed.

Description

technical field [0001] The invention relates to a computer technology, in particular to a method for estimating the conversion rate of an Internet advertisement based on a time information integration model, which can estimate the conversion rate of an advertisement based on historical advertisement conversion data of an advertising system, and assist in the precise delivery of advertisements. Background technique [0002] Internet advertising is to place advertisements on the Internet through online advertising platforms. It is a high-tech advertising operation method that publishes or publishes advertisements on the Internet by means of advertisement banners, text links, and multimedia on the website, and delivers them to Internet users through the Internet. Computational advertising is one of the most important business models on the Internet. The effectiveness of advertising is usually measured through exposure, clicks, and conversion. Among them, the advertising convers...

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): G06Q30/02G06Q10/04G06K9/62
CPCG06Q10/04G06Q30/0242G06F18/24323
Inventor 严建峰周捷杨璐
Owner SUZHOU UNIV
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