A collaborative filtering recommendation algorithm based on contents' genome

Abstract

The technology of personalized recommendation has two kinds of advantages: initiative and timeliness, it is an important way to solve the problem of overloaded information. Currently, as a kind of the personalized recommendation technology, the collaborative filtering technology is used most. The algorithm is roughly divided into two versions: user-based collaborative filtering and content-based collaborative filtering algorithm. The latter is more suitable in mass recommendation object, but it is low in calculation accuracy of similarity. So, this paper proposes the concept of the genome of contents to solve the problem of low accuracy leaded by the content-based collaborative filtering recommendation algorithm in mass recommendation object. It is called collaborative filtering algorithm based on the contents of the genome, and it can improve the precision and accuracy of calculation of contents similarity.