适应用户兴趣变化的指数遗忘协同过滤算法

协同过滤是目前推荐系统中最为成功的推荐技术，但传统的协同过滤算法没有考虑用户兴趣的变化。针对上述问题，从艾宾浩斯记忆遗忘规律得到启发，提出一种基于资源相似度的协同过滤算法，利用基于指数遗忘的数据权重来逐步减小资源相似度的权重。实验结果表明，该算法显著提高推荐系统的推荐质量。

Exponential forgetting collaborative filtering recommendation algorithm incorporated with user interest change

Collaborative Filtering（CF） is the most successful technologies to date,but traditional collaborative filtering algorithm does not consider the change of users’interests.To solve the problem,this paper presents a CF recommendation algorithm,named item similarity-based CF algorithm,which uses exponential gradual forgetting-based data weight to diminish the importance of each item similarity.The experimental results show that the proposed algorithm can efficiently improve recommendation quality.