基于条件型游走二部图协同过滤算法

针对拥有少量评分的新用户采用传统方法很难找到目标用户的最近邻居集的问题，本文提出了一种条件型游走二部图协同过滤算法。该算法根据复杂网络理论的二部图网络，将用户-项目评分矩阵转换为用户-项目二部图，采用了条件型游走计算目标用户与其他用户之间的相似性。研究结果表明在同样的数据稀疏性情况下，本文提出的条件型游走二部图协同过滤算法在MAE和准确率都要优于其他两种传统的协同过滤算法，从而提高了算法的推荐精度；而且当训练值的比例很低时，即数据稀疏程度越大时，本文提出的推荐算法的对推荐质量的提高程度越大。

Collaborative Filtering Algorithm Based on Conditional Walk Bipartite Graph

For new users with a small number of rating, it is difficult to find the approximate neighbor set of the target user by the traditional method, In this paper, we propose a collaborative filtering algorithm based on conditional walk Bipartite graph. Based on the bipartite graph network of the complex network theory, the item scoring matrix is transformed into user-project bipartite graphs, the conditional walk is used to calculate the similarity between the target user and other users. The results show that under the same data sparsity condition, the conditional swarm bipartite cooperative filtering algorithm proposed in this chapter is better than the other two traditional collaborative filtering algorithms in MAE and precision, and the recommendation precision is improved. The higher the degree of data sparsity, the higher the recommendation quality of the recommendation algorithm based on conditional biped graph.