Learning Attribute-to-Feature Mappings for Cold-Start Recommendations

Abstract

Abstract-Cold-start scenarios in recommender systems are situations in which no prior events, like ratings or clicks, are known for certain users or items. To compute predictions in such cases, additional information about users (user attributes, e.g. gender, age, geographical location, occupation) and items (item attributes, e.g. genres, product categories, keywords) must be used.We describe a method that maps such entity (e.g. user or item) attributes to the latent features of a matrix (or higherdimensional) factorization model. With such mappings, the factors of a MF model trained by standard techniques can be applied to the new-user and the new-item problem, while retaining its advantages, in particular speed and predictive accuracy.We use the mapping concept to construct an attributeaware matrix factorization model for item recommendation from implicit, positive-only feedback. Experiments on the newitem problem show that this approach provides good predictive accuracy, while the prediction time only grows by a constant factor.

Link Prediction via Matrix Factorization

“…This issue has been studied in the context of the cold-start problem [29] in collaborative filtering. Recent advances in this literature are based on inferring reasonable values of latent features by falling back to the side information as a prior [2,12]. However, unlike most collaborative filtering applications, in link prediction we are mostly interested in using side information to improve predictions, rather than dealing with cold-start nodes.…”

Learning Translations via Matrix Completion

“…However, due to the sparsity of existing bilingual dictionaries (for some language pairs such dictionaries may not exist), the traditional formulation of MF with BPR suffers from the "cold start" issue (Gantner et al, 2010;He and McAuley, 2016;Verga et al, 2016). In our case, these are situations in which some source words have no translations to any word in the target or related languages.…”

Factorization Techniques for Predicting Student Performance

“…We treat this problem with a simple strategy: providing the global average score for the new users or new items. Of course, more sophisticated methods can improve the prediction results (Preisach et al, 2010;Gantner et al, 2010) but we leave these solutions for future work. Moreover, in the educational data mining scenario, the cold-start problem is not as harmful as in the e-commerce environment where the new users and new items appear every day or even hour.…”