A Collaborative Filtering Recommendation Method Combining Approximation Algorithms

Abstract

Collaborative filtering (CF) recommendation is a classic and practical recommendation method. This paper proposes a new method to improve collaborative filtering recommendation, treating the solution of the recommendation problem as an approximate problem, and uses the greedy strategy to solve the optimization problem. In this paper, the similarity calculation method of collaborative filtering algorithm is also modified. Researchers found that this improvement greatly improved the efficiency of the algorithm. Compared with the traditional algorithm, the accuracy has also made great progress. It is a successful experiment.