Two-Stage Session-based Recommendations with Candidate Rank Embeddings
This work addresses the challenge of improving recommendation accuracy for e-commerce platforms like Zalando, though it appears incremental as it builds on existing methods like STAMP and NARM.
The paper tackles the problem of similar-item recommendation in session-based systems by enhancing the rank of the most relevant items using a Candidate Rank Embedding, resulting in significant improvements in Recall, MRR at 20, and Click Through Rate on the Fashion-Similar dataset and public datasets.
Recent advances in Session-based recommender systems have gained attention due to their potential of providing real-time personalized recommendations with high recall, especially when compared to traditional methods like matrix factorization and item-based collaborative filtering. Nowadays, two of the most recent methods are Short-Term Attention/Memory Priority Model for Session-based Recommendation (STAMP) and Neural Attentive Session-based Recommendation (NARM). However, when these two methods were applied in the similar-item recommendation dataset of Zalando (Fashion-Similar), they did not work out-of-the-box compared to a simple Collaborative-Filtering approach. Aiming for improving the similar-item recommendation, we propose to concentrate efforts on enhancing the rank of the few most relevant items from the original recommendations, by employing the information of the session of the user encoded by an attention network. The efficacy of this strategy was confirmed when using a novel Candidate Rank Embedding that encodes the global ranking information of each candidate in the re-ranking process. Experimental results in Fashion-Similar show significant improvements over the baseline on Recall and MRR at 20, as well as improvements in Click Through Rate based on an online test. Additionally, it is important to point out from the evaluation that was performed the potential of this method on the next click prediction problem because when applied to STAMP and NARM, it improves the Recall and MRR at 20 on two publicly available real-world datasets.