The Collaborative Filtering Recommendation Algorithm Based on BP Neural Networks

• Published in: 2009 International Symposium on Intelligent Ubiquitous Computing and Education : 15-16 May 2009 pp. 234 - 236
• Main Author: Dan-Er Chen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2009
• Subjects: BP neural networks; Collaboration; collaborative filtering; Digital filters; e-commerce; Filtering algorithms; Information filtering; Information filters; Internet; Nearest neighbor searches; Neural networks; recommender system; Recommender systems; Software libraries
• ISBN: 9780769536194; 0769536190
• DOI: 10.1109/IUCE.2009.121

Collaborative filtering is one of the most successful technologies in recommender systems, and widely used in many personalized recommender areas with the development of Internet, such as e-commerce, digital library and so on. The K-nearest neighbor method is a popular way for the collaborative filtering realizations. Its key technique is to find k nearest neighbors for a given user to predict his interests. However, most collaborative filtering algorithms suffer from data sparsity which leads to inaccuracy of recommendation. Aiming at the problem of data sparsity for collaborative filtering, a collaborative filtering algorithm based on BP neural networks is presented. This method uses the BP neural networks to fill the vacant ratings at first, then uses collaborative filtering to form nearest neighborhood, and lastly generates recommendations. The collaborative filtering based on BP neural networks smoothing can produce more accuracy recommendation than the traditional method.