A New Prediction Approach Based on Linear Regression for Collaborative Filtering

Abstract—Recommender systems using collaborative filtering help users filter information based on previous knowledge of users ’ preferences. Most of existing recommender systems make predictions using weighted average method. This paper introduces a new prediction approach based on an effective linear regression model. One fundamental idea behind this approach is that there exist patterns among different users ’ preferences. And we propose a linear regression model to characterize the inner relationships among different users ’ rating habits. The major contribution of this approach is that it can make more accurate predictions via utilizing the exact linear correlation indicated by Pearson Correlation Coefficient directly. The preliminary experiments show that our approach can improve the accuracy of prediction thus make recommendations more appealing to users