Skip to yearly menu bar Skip to main content


Learning to select for a predefined ranking

Aleksei Ustimenko · Aleksandr Vorobev · Gleb Gusev · Pavel Serdyukov

Pacific Ballroom #228

Keywords: [ Supervised Learning ] [ Ranking and Preference Learning ] [ Non-convex Optimization ] [ Information Retrieval ]


In this paper, we formulate a novel problem of learning to select a set of items maximizing the quality of their ordered list, where the order is predefined by some explicit rule. Unlike the classic information retrieval problem, in our setting, the predefined order of items in the list may not correspond to their quality in general. For example, this is a dominant scenario in personalized news and social media feeds, where items are ordered by publication time in a user interface. We propose new theoretically grounded algorithms based on direct optimization of the resulting list quality. Our offline and online experiments with a large-scale product search engine demonstrate the overwhelming advantage of our methods over the baselines in terms of all key quality metrics.

Live content is unavailable. Log in and register to view live content