Research on ranking recommendation algorithm of multi-B2C behavior

Although personalized recommendation technology has been widely used in the Internet, there are still some problems which should be solved, such as data sparseness problem, “cold start” problem. The paper proposes a multi-B2C crossing ranking recommendation algorithm. According to the new user “cold start” problem, the paper proposes different categories of electronic commerce website access multi-B2C behavior information recommendation. Experiments show that the algorithm is accurate and personalized recommendation.