The Recommendation Systems task is to produce a list of recommendations for a user. The most common methods used in recommender systems are factor models (Koren et al., 2009; Weimer et al., 2007; Hidasi & Tikk, 2012) and neighborhood methods (Sarwar et al., 2001; Koren, 2008). Factor models work by decomposing the sparse user-item interactions matrix to a set of d dimensional vectors one for each item and user in the dataset. Factor models are hard to apply in session-based recommendations due to the absence of a user profile. On the other hand, neighborhood methods, which rely on computing similarities between items (or users) are based on co-occurrences of items in sessions (or user profiles). Neighborhood methods have been used extensively in session-based recommendations.

( Image credit: CuMF_SGD )