Recommender systems act as decision support in supporting users selecting the right choice of items or services from a high number choices an overloaded search space. However, such have difficulty dealing with sparse rating data. One way to deal this issue is incorporate additional explicit information, also known side information. information requires some action and often not always available...

In an earlier study, Swain et al. reported on two statistical separability measures which for multiclass feature selection were shown experimentally to be more reliable than divergence. However, the empirical results of that study together with the best theoretical results in the literature left open some practical questions regarding the quantitative characterization of these separability meas...