IRLGApr 11, 2021

Dynamic Modeling of User Preferences for Stable Recommendations

arXiv:2104.05047v110 citations
Originality Incremental advance
AI Analysis

This work addresses the issue of user distrust and poor personalization in recommender systems for domains where preferences are stable, representing an incremental improvement to existing methods.

The paper tackled the problem of unstable recommendations in domains with long-term user preferences by proposing an incremental learning scheme that dynamically models user preferences, resulting in significantly improved stability without sacrificing accuracy in top-n recommendation tasks.

In domains where users tend to develop long-term preferences that do not change too frequently, the stability of recommendations is an important factor of the perceived quality of a recommender system. In such cases, unstable recommendations may lead to poor personalization experience and distrust, driving users away from a recommendation service. We propose an incremental learning scheme that mitigates such problems through the dynamic modeling approach. It incorporates a generalized matrix form of a partial differential equation integrator that yields a dynamic low-rank approximation of time-dependent matrices representing user preferences. The scheme allows extending the famous PureSVD approach to time-aware settings and significantly improves its stability without sacrificing the accuracy in standard top-$n$ recommendations tasks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes