Recommender systems: when memory matters
This work addresses performance improvements in recommender systems for users and platforms, but it appears incremental as it builds on existing sequential methods by incorporating long memory filtering.
The paper tackles the problem of improving sequential recommender systems by studying the effect of long memory in user interactions, proposing an online algorithm that updates parameters per user over blocks of items, and shows substantial performance gains in MAP and NDCG, especially for large-scale systems.
In this paper, we study the effect of long memory in the learnability of a sequential recommender system including users' implicit feedback. We propose an online algorithm, where model parameters are updated user per user over blocks of items constituted by a sequence of unclicked items followed by a clicked one. We illustrate through thorough empirical evaluations that filtering users with respect to the degree of long memory contained in their interactions with the system allows to substantially gain in performance with respect to MAP and NDCG, especially in the context of training large-scale Recommender Systems.