Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for predicting user basic attributes based on ensemble learning

A basic attribute and integrated learning technology, applied in the field of integrated learning, can solve the problems of less data mining of user App usage and low prediction accuracy of basic attributes

Active Publication Date: 2021-04-20
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the problems of less mining of user App usage data and low prediction accuracy of basic attributes in existing methods, the present invention mines and predicts user basic attributes based on App installation and usage 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
  • A method for predicting user basic attributes based on ensemble learning
  • A method for predicting user basic attributes based on ensemble learning
  • A method for predicting user basic attributes based on ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Specific embodiments of the present invention will be described below in conjunction with the accompanying drawings, so that those skilled in the art can better understand the present invention.

[0041] In this example, if figure 1 As shown, the algorithm flow of the method proposed by the present invention is provided:

[0042] Step 1: Data collection and preprocessing

[0043]Collect the App usage behavior records of a large number of users. The App usage behavior records include the user ID, user gender and age, the list of Apps installed by the user, and the opening and closing time of each App in the list. The gender of the user is male and female, recorded as 1 and 2 respectively; the age of the user is divided into 11 intervals, marked as 0 (60). Since gender and age are mutually influencing and coupled cross attributes, the present invention combines gender and age into 22 categories for multi-category prediction, and the combined gender-age grouping is recor...

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 a user basic attribute prediction method based on integrated learning. The method predicts the user's age and gender by analyzing the mobile user's App installation and usage data. First, the multi-classification problem is transformed into multiple binary classification problems, and the LightGBM and FM fusion model is used as a binary classifier to predict the binary classification; then the prediction results of the binary classification are combined with the original features to build a multi-classification model. Experimental results show that the fusion method proposed by the present invention can improve the effect of user attribute prediction.

Description

technical field [0001] The invention relates to the technical field of integrated learning, and specifically designs a user basic attribute prediction method based on smart phone App installation and usage data. Background technique [0002] With the development of the mobile Internet, smartphones have become the most mobile devices people own. At present, the number of Apps available in the App Store has exceeded 4 million, and the Apps that people install and use may be closely related to their basic attributes such as gender and age. This information can reflect personal information such as the user's basic attributes, interests and preferences, and living habits. In-depth mining of user attributes can not only help app stores understand user behavior characteristics and recommend products in a targeted manner; it can also help companies place Internet advertisements more accurately and save advertising costs. [0003] At present, the existing research is mainly based o...

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): G06K9/62G06F11/34
CPCG06F11/3438G06F18/2431G06F18/254G06F18/214
Inventor 曹倩王曼刘立红左敏李海生
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY