Recommendation system of e-commerce based on improved collaborative filtering algorithm
Xiaoying Wang, Chengliang Wang · 2017
With the rapid development of information technology, the information overload problem in e-commerce site is becoming increasingly serious. It is difficult for people to obtain their own needs from the massive items information quickly. Recommendation systems contribute to alleviating the problem of information overload that exists on the e-commerce site. Collaborative filtering algorithm is most widely used in the recommendation algorithm, but there are still sparse data problems in collaborative filtering algorithm. In this paper, an e-commerce recommendation system based on improved user-based cooperative filtering algorithm is presented, which attempt to bridge the sparsity problem by combining the characteristics of user ratings with user reviews, and using the theme LDA model based on Spark framework to extract user preference.