Beyond Static Calibration: The Impact of User Preference Dynamics on Calibrated Recommendation

TL;DR

This paper explores how user preference changes over time influence the calibration of recommender systems, highlighting the importance of considering preference dynamics for more accurate and user-aligned recommendations.

Contribution

It introduces a granular, time-sensitive approach to calibration that accounts for evolving user preferences, challenging the static assumption in traditional methods.

Findings

Preference dynamics significantly impact calibration accuracy.

Recent user interactions are more relevant for calibration.

Different domains exhibit distinct preference evolution patterns.

Abstract

Calibration in recommender systems is an important performance criterion that ensures consistency between the distribution of user preference categories and that of recommendations generated by the system. Standard methods for mitigating miscalibration typically assume that user preference profiles are static, and they measure calibration relative to the full history of user's interactions, including possibly outdated and stale preference categories. We conjecture that this approach can lead to recommendations that, while appearing calibrated, in fact, distort users' true preferences. In this paper, we conduct a preliminary investigation of recommendation calibration at a more granular level, taking into account evolving user preferences. By analyzing differently sized training time windows from the most recent interactions to the oldest, we identify the most relevant segment of user's preferences that optimizes the calibration metric. We perform an exploratory analysis with datasets from different domains with distinctive user-interaction characteristics. We demonstrate how the evolving nature of user preferences affects recommendation calibration, and how this effect is manifested differently depending on the characteristics of the data in a given domain. Datasets, codes, and more detailed experimental results are available at: https://github.com/nicolelin13/DynamicCalibrationUMAP.