Gal A. Kaminka: Publications

Sorted by DateClassified by Publication TypeClassified by TopicGrouped by Student (current)Grouped by Former Students

Learning User Boredom Constraints in Sequential Recommender Systems

Noam Zvi and Gal A. Kaminka. Learning User Boredom Constraints in Sequential Recommender Systems . In Proceedings of the AAMAS Workshop on Adaptive and Learning Agents (ALA), 2026.

Download

(unavailable)

Abstract

We consider sequential recommender systems that work in multiple sessions, with a fixed catalog. Each session opens with a single recommendation. Acceptance leads to another recommendation. The session ends upon first rejection. The goal is to maximize session length. Myopic exploitation of previously-successful recommendations quickly leads to user boredom. We introduce novel bandit algorithms that improve recommendation variety by learning and enforcing per-user, per-item boredom thresholds. This allows repeated recommendations, appropriately spaced in time, with a high acceptance rate. Learning takes place in two stages: (i) item-specific boredom thresholds are determined; (ii) once the thresholds are known, preference for the item is learned via a standard bandit algorithm. Evaluation using user data from a commercial system demonstrates clear improvements in session length.

BibTeX

@inproceedings{ala26ws-noam,
		title = {	Learning User Boredom Constraints in Sequential Recommender Systems },
		author = {Noam Zvi and Gal A. Kaminka},
		booktitle = {Proceedings of the {AAMAS} Workshop on Adaptive and Learning Agents ({ALA})},
  	year = {2026},
  	abstract = { We consider sequential recommender systems that work in multiple sessions, with a fixed catalog. Each session opens with a single recommendation. Acceptance leads to another recommendation. The session ends upon first rejection. The goal is to maximize session length. Myopic exploitation of previously-successful recommendations quickly leads to user boredom. We introduce novel bandit algorithms that improve recommendation variety by learning and enforcing per-user, per-item boredom thresholds. This allows repeated recommendations, appropriately spaced in time, with a high acceptance rate. Learning takes place in two stages: (i) item-specific boredom thresholds are determined; (ii) once the thresholds are known, preference for the item is learned via a standard bandit algorithm. Evaluation using user data from a commercial system demonstrates clear improvements in session length.
    },
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Apr 06, 2026 23:33:57