基于用户的优化协同过滤推荐算法

Collaborative Filtering Recommendation Optimization Based on User

针对传统的协同过滤推荐算法存在的用户邻居集选择不准确问题,论文提出了一种优化的协同过滤推荐算法,选择用户的共同评分数据计算用户的相似性,同时考虑共同评分数据中用户对项目评分的一致性,构造评分一致矩阵,将用户评分一致次数与评分项目数之比作为惩罚函数引入到相似度的计算中,缓解相似度计算值与实际值出现的偏差。实验表明,提出的优化算法显著提高了预测的准确性,从而提高了推荐质量。

In order to improve accuracy of the traditional collaborative filtering algorithm select user neighbor set,this paper proposes an improved collaborative filtering recommendation algorithm.The algorithm selects the user common rating data to calculate the user＇s similarity,also considers the consistency of the score data,constructes evaluation matrix,and alleviates the similarity calculation value and actual value deviation by user rating consistent times thanratingitem number as a penalty function is introduced into the similarity calculation.Experimental results show that the improved algorithm proposed in this paper significantly increases the prediction accuracy,so as to improve the quality of recommendation.