Optimal Sequential Recommendations: Exploiting User and Item Structure

Mina Karzand

doi:10.1109/tit.2026.3654181

Optimal Sequential Recommendations: Exploiting User and Item Structure

2026-05-01

0

PRE

AI

DOI：10.1109/tit.2026.3654181

Original

Original request for help

Save

Abstract

En 中文

We consider an online model for recommendation systems, with each user being recommended an item at each time-step and providing 'like' or 'dislike' feedback. A latent variable model specifies the user preferences: both users and items are clustered into types. The model captures structure in both the item and user spaces, as used by item-item and user-user collaborative filtering algorithms. We study the situation in which the type preference matrix has i.i.d. entries. Our main contribution is an algorithm that simultaneously uses both item and user structures, proved to be near-optimal via corresponding information-theoretic lower bounds. In particular, our analysis highlights the sub-optimality of using only one of item or user structure (as is done in most collaborative filtering algorithms).

Keywords:

Lower bound

Recommender systems

Costs

Information theory

Collaborative filtering

Heuristic algorithms

Clustering algorithms

Upper bound

Motion pictures

Artificial intelligence

Recommendation systems

collaborative filtering

online algorithms

optimal regret

Optimal Sequential Recommendations: Exploiting User and Item Structure

Abstract

Journal

Organization

Cited Papers