Correlation analysis algorithm based commodity recommendation method

Abstract

The present invention relates to a commodity recommendation method based on an association analysis algorithm. Commodity recommendation is performed according to user behavior logs in shopping websites. Carry out fuzzy clustering analysis with products to generate multiple user groups and product categories, and each user group’s evaluation score for each product category; S2, build recommendation matrix M; S3, obtain new user behavior logs, use recommendation matrix M recommends products to users in the newly added user behavior log; S4, judges whether the data volume of the newly added user behavior log has reached the set value, if so, returns to step S1, and counts the data volume of the newly added user behavior log value, if not, return to step S3. Compared with the prior art, the present invention has the advantages of small amount of calculation, high reliability and strong pertinence, and has adaptability to constantly changing market consumption trends.

Description

technical field [0001] The invention relates to a method for recommending online commodities, in particular to a method for recommending commodities based on an association analysis algorithm. Background technique [0002] Product recommendation algorithms used by shopping websites usually include: [0003] The user-based collaborative filtering algorithm takes each user as the subject of analysis, and for each group, calculates the degree of association between each user of the group and other users of the group by processing the product browsing logs of each user in the group , and then recommend to the user the products that he has not browsed or purchased but is purchased or browsed by other users with high correlation in the group; the disadvantage of this algorithm is that the user increases rapidly, but only the user's historical preference data is used to calculate the user similarity degree, there is a "cold start" problem for new users. [0004] The model-based c...

AI Technical Summary

Problems solved by technology

[0003] The user-based collaborative filtering algorithm takes each user as the subject of analysis, and for each group, calculates the degree of association between each user in the group and other users in the group by processing the product browsing logs of each user in the group , and then recommend to the user the products that he has not browsed or purchased but is purchased or browsed by other users with high correlation in the group; the disadvantage of this algorithm is that the user increases rapidly, but only the user's historical preference data is used to calculate the user similarity degree, there is a "cold start" problem for new users

The disadvantage of this algorithm is: the time required to create the matrix increases rapidly with the increase in the number of users and products. Once the new user's ratings for the products are received, the original matrix will become invalid and must be updated, which has poor flexibility.

Images