Balázs Hidasi

Balázs Hidasi, Alexandros Karatzoglou

RNNs have been shown to be excellent models for sequential data and in particular for data that is generated by users in an session-based manner. The use of RNNs provides impressive performance benefits over classical methods in session-based recommendations. In this work we introduce novel ranking loss functions tailored to RNNs in the recommendation setting. The improved performance of these losses over alternatives, along with further tricks and refinements described in this work, allow for an overall improvement of up to 35% in terms of MRR and Recall@20 over previous session-based RNN solutions and up to 53% over classical collaborative filtering approaches. Unlike data augmentation-based improvements, our method does not increase training times significantly. We further demonstrate the performance gain of the RNN over baselines in an online A/B test.

Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas et al.

We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNN-based approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches.

Balázs Hidasi, Domonkos Tikk

Albeit the implicit feedback based recommendation problem - when only the user history is available but there are no ratings - is the most typical setting in real-world applications, it is much less researched than the explicit feedback case. State-of-the-art algorithms that are efficient on the explicit case cannot be automatically transformed to the implicit case if scalability should be maintained. There are few implicit feedback benchmark data sets, therefore new ideas are usually experimented on explicit benchmarks. In this paper, we propose a generic context-aware implicit feedback recommender algorithm, coined iTALS. iTALS applies a fast, ALS-based tensor factorization learning method that scales linearly with the number of non-zero elements in the tensor. We also present two approximate and faster variants of iTALS using coordinate descent and conjugate gradient methods at learning. The method also allows us to incorporate various contextual information into the model while maintaining its computational efficiency. We present two context-aware variants of iTALS incorporating seasonality and item purchase sequentiality into the model to distinguish user behavior at different time intervals, and product types with different repetitiveness. Experiments run on six data sets shows that iTALS clearly outperforms context-unaware models and context aware baselines, while it is on par with factorization machines (beats 7 times out of 12 cases) both in terms of recall and MAP.