Explainable Personalized Sequential Recommendation Using Attention-fused Recurrent Networks

What is it about?

The emerging meta- and multi-verse landscape is yet another step towards the more prevalent use of already ubiquitous online markets. In such markets, recommender systems play critical roles by offering items of interest to the users, thereby narrowing down a vast search space that comprises hundreds of thousands of products. Recommender systems are usually designed to learn common user behaviors and rely on them for inference. This approach, while effective, is oblivious to subtle idiosyncrasies that differentiate humans from each other. Focusing on this observation, we propose an architecture that relies on common patterns as well as individual behaviors to tailor its recommendations for each person. Simulations under a controlled environment show that our proposed model learns interpretable personalized user behaviors. Our empirical results on Nielsen Consumer Panel dataset indicate that the proposed approach achieves up to 27.9% performance improvement compared to the state-of-the-art.

Featured Image

Photo by Alexas_Fotos on Unsplash

Photo by Alexas_Fotos on Unsplash

Why is it important?

The key contributions of our work are: - We propose a model that uses attention layers combined with RNNs for the task of sequential recommendation. We show that our model outperforms various state-of-the-art methods on synthetic and real-world data under different evaluation metrics. - We test our model in a controlled environment of a synthetic dataset. we show that our model learns personalized user behaviors and offers interpretable results through visualizing item relationships. - We conduct an ablation study on variations of the proposed model to evaluate the contribution of components of the model and report the most effective architecture.

Perspectives