Method and system for user grouping for optimizing advertising

A user grouping and user group technology, applied in advertising, data processing applications, machine learning, etc., can solve problems such as limiting user base and reducing overall user exposure, achieving accurate prediction, fine-grained and accurate user management, and small deviations. Effect

Active Publication Date: 2022-05-27
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

While showing ads to only a few users with a high conversion rate can provide short-term benefits, it limits the user base (e.g., the number of users who receive an ad) and can lead to reduced overall user exposure

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 user grouping for optimizing advertising
  • Method and system for user grouping for optimizing advertising
  • Method and system for user grouping for optimizing advertising

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The techniques disclosed herein can optimize the accuracy and overall efficiency of online advertising. In some embodiments, a page (eg, a web page, an application's homepage, a message) may have several advertising slots (eg, banners) that display promotions, advertisements, coupons, etc. to the user. Although the number of ad slots is highly limited (eg, three or less for a good user experience), the number of candidate ads is typically in the millions. To maximize overall exposure, the platform hosting the page (eg, search engine, e-commerce platform, mobile app) can selectively display certain advertisements to users. These selected ads should yield the best conversion rates when served to users. In this context, an advertisement may refer to a single advertisement or a group of advertisements (eg, one or more advertisements that share similar target users on a common theme). Conversion rate can refer to the probability that a user clicks on an ad, or the probabil...

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

Provided herein are methods, systems and apparatus, including computer programs encoded on computer storage media, for grouping users. An embodiment of the method includes: dividing a plurality of users targeted by a candidate advertisement into a plurality of user buckets, wherein each of the plurality of user buckets has a first conversion score associated with it; a corresponding trained predictive model, wherein the trained predictive model is capable of predicting based on at least a first conversion score associated with a user bucket and a second conversion score associated with a set of user buckets including the user bucket a conversion score; and constructing an optimization model using the trained predictive model, wherein the objective function of the optimization problem is to maximize the total conversion score using the grouping strategy determined by solving the optimization problem.

Description

technical field [0001] The present disclosure relates generally to systems and methods for optimizing online advertising delivery, and more particularly to systems and methods for optimizing user grouping for online advertising delivery. Background technique [0002] Online advertising is a form of marketing and advertising that uses the Internet to deliver promotional marketing messages (eg, advertisements, promotions, coupons) to users. Typically, an advertisement may be targeted to users with certain characteristics based on the product and / or person being promoted by the advertiser. [0003] When determining which advertisements to display to a user, a host (eg, search engine, website) may first identify candidate advertisements targeting the user, and then select one or more of them to display to the user (eg, depending on number of ad slots available). [0004] Traditionally, users targeted by ads are divided into groups based on the user's conversion rate. Typicall...

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): G06Q30/02
CPCG06Q30/0244G06Q30/0251G06Q30/0277G06N20/00G06Q30/0254
Inventor 严佳华致刚奇峰刘颖琪操颖平
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
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