结合概率矩阵分解的混合型推荐算法

Hybrid recommendation algorithm based on probability matrix factorization

针对社交网络推荐系统中存在的数据稀疏、冷启动等问题,提出了一种结合特征传递和概率矩阵分解(TPMF)的社交网络混合型推荐算法。以概率矩阵因式分解(PMF)方法作为推荐框架,不仅考虑了用户信任网络,还结合推荐项目之间的关联关系、用户项目评分矩阵和自适应权重来权衡个人潜在特征和社交潜在特征对用户的影响程度。将社交网络中用户间的信任特征传递引入推荐系统中作为推荐的有效依据。实验结果表明,与基于用户的协同过滤(UBCF)、TidalTrust、PMF和SoRec算法相比,TPMF的平均绝对误差(MAE)直接相减后降低了4.1%到20.8%,均方根误差(RMSE)降低了3.3%到18.5%。在冷启动问题中,与上述四种算法相比,TPMF的平均绝对误差相减后降低了1.6%到14.7%,均方根误差降低了约1.2%到9.7%,能有效缓解冷启动问题,提高算法的鲁棒性。

Aiming at the problems of data sparseness and cold start in social network recommendation systems, a hybrid social network recommendation algorithm based on feature Transform and Probabilistic Matrix Factorization （TPMF） was proposed. Using Probability Matrix Factorization （PMF） method as recommendation framework, trust network, the relationship between the recommended items, user-item score matrix and adaptive weight were combined to balance the impact of individual and social potential characteristics on users. The trust feature transfer was introduced into the recommendation system as valid basis for recommendation. Compared to the User-Based Collaborative Filtering （UBCF）, TidalTrust, PMF and SoRec, the experimental results show that the Mean Absolute Error （MAE） of TPMF was decreased by 4.1% to 20.8%, and the Root Mean Square Error （RMSE） of TPMF was decreased by 3.3% to 18.5%. Compared with the above four algorithms, for the cold start problem, the Mean Absolute Error was decreased by 1.6 to 14.7%, and the RMSE was decreased by 1.2% to 9.7%, which verifies TPMF effectively alleviates cold start problem and improves the robustness of the algorithm.