Application of recommended methods and devices

Abstract

The invention discloses an application recommendation method and device, and belongs to the field of network technology. The method includes: acquiring relevance of each of multiple applications and credit investigation characteristics of multiple users; grouping the multiple applications according to the relevance to obtain a first application group, wherein the first application group includes multiple applications of which relevance is greater than a preset threshold value; for the first application group, establishing a corresponding first prediction model on the basis of the credit investigation characteristics of the multiple users, wherein the first prediction model is used for determining recommendation probability of the applications on the basis of a credit investigation characteristic; and recommending applications to a to-be-recommended user on the basis of the credit investigation characteristic of the to-be-recommended user and the first prediction model. According to themethod, an accuracy rate of recommendation on the applications in the first application group can be increased, the recommended applications can be enabled to more accord with downloading requirements of the user, and thus conversion rates of the applications can be increased.

Description

technical field

[0001] The invention relates to the field of network technology, in particular to an application recommendation method and device. Background technique

[0002] With the continuous development of network technology, service providers provide more and more services to users through the network, and the services are becoming more and more perfect. For example, when a user wants to download an application, he may download a corresponding application on an application download platform or an application service platform by inputting a search keyword.

[0003] In addition to providing the application download function, the application download platform or application service platform can also recommend applications to users. The specific recommendation method can be: analyze user characteristics to recommend applications to different users in a targeted manner. Including age, gender, city, online interaction information and historical download records, etc. For ...

Images