Research Of Personalized Group-buying Recommendation System Based On Collaborative Filtering Algorithm

Recently, as a new mode of e-commerce, the group-buying has been developing rapidly. However, when faced with the problem of information overload. group-buying cannot provide users with personalized recommendation. This paper made a thorough research with Group-buying, discusses the existing problems when the traditional collaborative filtering algorithm is applied to the personalized recommendation system of group-buying websites and provides solutions for data sparse, cold start and lack of trust. Combined with the User-based CF and Item-based CF. this paper provides improved collaborative filtering algorithm, which is applied in the personalized recommendation system of group-buying website. In addition, this paper use the double recommend model. Finally, in order to verify the validity of the improved algorithm, this paper simulation experiments, the experimental results show that the improved algorithm in the recommended effect is obviously better than the traditional algorithm.