Deviation-based and similarity-based contextual SLIM recommendation algorithms

摘要: Context-aware recommender systems (CARS) have been demonstrated to be able enhance recommendations by adapting users' preferences different contextual situations. In recent years, several CARS algorithms developed incorporated into the systems. For example, differential context modeling (DCM) was modified based on traditional neighborhood collaborative filtering (NBCF), context-aware matrix factorization (CAMF) coupled dependency with technique (MF), and tensor directly models contexts as additional dimensions in multi-dimensional space, etc. CAMF works well but it is difficult interpret latent features algorithm. DCM good for explanation may only work data sets dense ratings. Recently, we successfully incorporate Sparse LInear Method (SLIM) develop SLIM (CSLIM) recommendation which take advantages of both NBCF MF. CSLIM are more effective promising recommenders. this work, provide introduction framework algorithms, present current state research, discuss our ongoing future improve recommendations.