Determinantal point processes (DPPs) have received significant attention in the recent years as an elegant model for a variety of machine learning tasks, due to their ability to elegantly model set diversity and item quality or popularity. Recent work has shown that DPPs can be effective models for product recommendation and basket completion tasks. We present an enhanced DPP model that is specialized for the task of basket completion, the multi-task DPP. We view the basket completion problem as a multi-class classification problem, and leverage ideas from tensor factorization and multi-class classification to design the multi-task DPP model. We evaluate our model on several real-world datasets, and find that the multi-task DPP provides significantly better predictive quality than a number of state-of-the-art models.

Many modern recommender systems rely on matrix factor-ization techniques to produce personalized recommendationson the basis of the feedback that users provided on differ-ent items in the past. The feedback may take different forms,such as the rating of a movie, or the number of times a userlistened to the songs of a given music band. Nonetheless, insome situations, the user can perform several actions on eachitem, and the feedback is multidimensional (e.g., the user ofan e-commerce website can either click on a product, add theproduct to her cart or buy it). In this case, one can no longerview the recommendation problem as a matrix completion,unless the problem is reduced to a series of multiple inde-pendent problems, thus loosing the correlation between thedifferent actions. In this case, the most suitable approach is touse a tensor approach to learn all dimensions of the feedbacksimultaneously. In this paper, we propose a specific instanceof tensor completion and we show how it can be heavily par-allelized over both the dimensions (i.e., items, users, actions)and within each dimension (i.e., each item separately). Wevalidate the proposed method both in terms of prediction ac-curacy and scalability to large datasets.