欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
基于信任的协同过滤推荐算法在缓解数据稀疏性、提高推荐准确度上具有明显优势．在协同过滤推荐算法中引入信任关系需要解决两个问题：一是信任数据的获取与信任的度量问题，二是信任度与具体算法的结合问题．传统算法在解决这两个问题时，仍存在信任信息挖掘不足、利用率不高的现象，导致推荐准确率难以进一步提升．为此，引入用户可信度的概念，提出一种改进的奇异值分解算法，算法同时考虑了用户的信任信息、被信任信息以及各自的隐性反馈．在真实数据集上的实验结果表明：与传统算法和其他主流信任算法相比，本文算法能有效提高推荐准确度．
英文摘要：
Recommender algorithms based on trust perform better in alleviating data sparsity. However, there remain shortages in the process of obtaining trust information and defining trust degree, and in the process of mining trust relation in specific algorithms, which limit the improvement of prediction accuracy. To address this problem, the paper proposes user reliability and merges it into an im- proved singular value decomposition algorithm which integrates truster-specific and trustee-specific information and the implicit feed- back of each when generating prediction. Experiments on real world dataset show that the proposed algorithm performs better than state-of-the-art recommender algorithms in prediction accuracy.
同期刊论文项目
同项目期刊论文
期刊信息
位置：