基于多重信任的协同过滤推荐算法

Collaborative Filtering Recommendation Algorithm Based on Multiple Trust

针对评分数据稀疏性和用户冷启动所导致的协同过滤推荐系统的准确度与覆盖率较低的问题,文中融合显性信任和隐性信任因素,提出了一种基于多重信任的协同过滤推荐算法。首先,依据用户间推荐评分的准确性与可依赖度因子,提出一种改进的均方差(Mean Squared Difference,MSD)信任度量方法,并在此基础上提出基于隐性信任信息的评分模型;其次,以最大信任传播距离为约束,提出一种显性信任信息的关系模型;最后,依据评分相似性与显性信任关系,利用0-1背包组合优化策略选择出目标用户的最优近邻集合,从而进行评分预测。在Epinions数据集上与多种主流算法的对比仿真实验结果表明,该算法通过引入有效评分和显性信任关系,极大地缓解了数据稀疏性和冷启动问题,并且在不牺牲覆盖率的条件下显著提升了推荐准确度。

Aiming at the reduction of accuracy and coverage for collaborative filtering recommendation system caused by sparseness of scoring data and cold start of users,this paper integratesd the explicit trust and implicit trust factors,and proposed a collaborative filtering recommendation algorithm based on multiple trust.Firstly,an improved Mean Squared Difference（MSD）trust metric method was proposed based on the accuracy and dependability factor of the recommended scores among users.Based on this,a scoring model based on implicit trust information was proposed.Secondly,regarding the maximum trust propagation distance as the constraint,a relational model of explicit trust information was proposed.Finally,based on the similarity between the score and the explicit trust,the optimal neighbor set of the target user was selected by the 0-1 backpack combination optimization strategy,and the scoring prediction was carried out.Comparisons of the simulation results with a variety of state-of-the-art algorithms on Epinions dataset demonstrate that the proposed algorithm can greatly alleviate the data sparsity and cold start problems by introducing effective score and explicit trust relationship,and significantly improve the recommendation accuracy while preserving good coverage.