Calibrated Recommendations for Users with Decaying Attention

TL;DR

This paper develops algorithms for recommendation systems to produce diverse, well-calibrated lists that reflect user interests across genres, accounting for the fact that user attention decreases as they view lower-ranked items.

Contribution

It introduces novel approximation algorithms for calibration in recommendation lists considering decaying user attention, extending beyond previous models assuming equal attention.

Findings

Provided a $(1-1/e)$-approximation algorithm for fine-grained genre mixtures.

Achieved a $2/3$-approximate greedy algorithm for coarse genre binning.

Extended calibration techniques to account for ordering effects due to decaying attention.

Abstract

Recommendation systems capable of providing diverse sets of results are a focus of increasing importance, with motivations ranging from fairness to novelty and other aspects of optimizing user experience. One form of diversity of recent interest is calibration, the notion that personalized recommendations should reflect the full distribution of a user's interests, rather than a single predominant category -- for instance, a user who mainly reads entertainment news but also wants to keep up with news on the environment and the economy would prefer to see a mixture of these genres, not solely entertainment news. Existing work has formulated calibration as a subset selection problem; this line of work observes that the formulation requires the unrealistic assumption that all recommended items receive equal consideration from the user, but leaves as an open question the more realistic setting in which user attention decays as they move down the list of results. In this paper, we consider calibration with decaying user attention under two different models. In both models, there is a set of underlying genres that items can belong to. In the first setting, where items are represented by fine-grained mixtures of genre percentages, we provide a $(1-1/e)$-approximation algorithm by extending techniques for constrained submodular optimization. In the second setting, where items are coarsely binned into a single genre each, we surpass the $(1-1/e)$ barrier imposed by submodular maximization and give a $2/3$-approximate greedy algorithm. Our work thus addresses the problem of capturing ordering effects due to decaying attention, allowing for the extension of near-optimal calibration from recommendation sets to recommendation lists.