A Score Prediction Method Based on Asymmetric Distance Construction Submatrix

Abstract

The present invention discloses a score prediction method based on asymmetric distance construction sub-matrix, using asymmetric distance to measure the relationship between each user-item score pair and anchor points, so that the interest of each anchor point neighborhood is as concentrated as possible Near the anchor point, the formed submatrix can better reflect the concentrated interest of a certain group of users than using symmetric distance, and the prediction result of the vacant items in the matrix will be better; use the clustering method to quickly find the density peak to select Anchor points, so that each anchor point has a large neighborhood density and is far apart from each other, resulting in a uniform distribution of the sub-matrix obtained by segmentation, which is representative and can effectively cover the original scoring matrix; using asymmetric distance Measure the relationship between each user-item score pair in the matrix and the anchor point, which reduces the penalty for the distance caused by too few scores under the symmetrical distance. For inactive users or unpopular items with a small number of scores , there will be a greater probability of being divided into sub-matrixes, which improves the coverage of the sub-matrix to the data.

Description

technical field [0001] The invention belongs to the field of personalized recommendation, and more specifically relates to a scoring prediction method based on asymmetric distance construction sub-matrix. Background technique [0002] With the advent of the web2.0 era and the great improvement of network bandwidth, various social networking platforms have begun to appear, and fragmented information has begun to flood people's lives. In order to solve the problem of information overload, the personalized recommendation system is more and more showing its important value. For example, in the field of e-commerce, the recommendation system builds the user's interest model based on the user's historical behavior information, calculates the user's liking for items they have not purchased, and then recommends items that the user may like. [0003] In practical applications, the prediction of user preferences is usually carried out by collaborative filtering method. The basic idea ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problem that the rating prediction result accuracy of the recommendation system in the prior art is limited

Images