Research on recommender algorithm optimization based on statistics and preference model

The personalized recommender system has become a research hotspot in the field of artificial intelligence (AI) because it can effectively deal with information overload. Cold start and data sparsity are two major challenges for smart recommender systems. This paper proposes an optimized recommender algorithm based on statistics and preference model that is able to solve the problems of data sparsity and cold start by means of statistics. Taking the film scoring system as the test object, the Gaussian model is established for the video type preference. The results show that the optimized algorithm can better deal with cold start and data sparsity, and achieve more accurate prediction recommender score.