Research on the Recommendation Algorithm Based on Distributed Representation and Recursive Neural Network
Lihong Dong, Xiao Ma · 2017
Nowadays, recommendation system has become an important means for e-commerce websites to improve users' stickiness and revenue. The behavior of users in the Internet can be divided into explicit feedback and implicit feedback. In the implicit feedback, the user does not explicitly express the preference of the commodity; The explicit feedback behavior includes the user's explicit behavior of the object's preferences. This paper presents a new recommendation algorithm based on distributed representation and recursive neural network.This algorithm,on the one hand, modeling the user's sequential behavior, on the other hand, the algorithm compromises users' preference for goods. The experiment shows that the algorithm has a good performance compared with the traditional algorithm in the public data set.