Recommendation model training method and device, and recommendation method and device

Abstract

The invention provides a recommendation model training method and device and a recommendation method and device. The training method of the recommendation model comprises the steps of determining first initial parameter values of training parameters in a to-be-trained recommendation model, wherein the first initial parameter values are target parameter values obtained after initial parameter values are iteratively updated by a click rate estimation model trained in advance; acquiring user characteristics of at least two sample users and attribute characteristics of at least two sample application programs; generating a positive sample of that the sample users purchase the exposed sample application programs and a negative sample of that the sample users do not purchase the exposed sample application programs based on the user characteristics and the attribute characteristics; and on the basis of a sample set comprising at least one positive sample and at least one negative sample and the first initial parameter value, training a to-be-trained recommendation model to obtain the recommendation model, and outputting the exposure conversion rate of each sample user on each sample application program by the recommendation model.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a method and device for training a recommendation model, a method and device for recommendation, a computing device, and a computer-readable storage medium. Background technique [0002] In some Internet products, in order to facilitate users to quickly find the products they want (such as APP), personalized recommendation is required, and the APP that the user is most likely to click to buy is recommended to the user to be recommended. [0003] At present, some platforms simply use traditional machine learning models (such as LR or GBDT models) to make recommendations based on the tags of users and apps when making APP recommendations. This method of using tags to recommend requires a lot of manpower to establish Labeling system, and it is easy to recommend inappropriate apps to users (for example: apps for pornography, gambling and drugs), and it does not make f...

AI Technical Summary

Problems solved by technology

[0003] At present, some platforms simply use traditional machine learning models (such as LR or GBDT models) to make recommendations based on the tags of users and apps when making APP recommendations. This method of using tags to recommend requires a lot of manpower to establish Labeling system, and it is easy to recommend unsuitable apps to users (for example: apps for pornography, gambling and drugs), and it does not make full use of the purchase data after clicking, which may cause apps with high click-through rates to have low purchase conversion rates after users click

Images