C2C E-Commerce Recommender System Based on Three-Dimensional Collaborative Filtering

Abstract

To solve the special recommendation problem in C2C e-commerce websites, a three-dimensional collaborative filtering recommendation method which can recommend seller and product combinations is proposed by extending the traditional two-dimensional collaborative filtering method. And a C2C e-commerce recommender system based on the proposed method is designed. The framework of the system and the key calculations in the recommendation process are discussed. The system firstly calculates seller similarities using seller features, and fills the rating set based on sales relations and seller similarities to solve the sparsity problem of the three-dimensional rating data. Then it calculates the buyer similarities using historical ratings, decides neighbors and predicts unknown ratings. Finally it recommends the seller and product combinations with the highest prediction ratings to the target buyer. A true data experiment proves the good recommendation performance of the system.