Constrained Multi-Slot Optimization for Ranking Recommendations

TL;DR

This paper introduces a constrained multi-slot optimization framework for ranking recommendations, modeling interactions among items across slots to improve multi-objective trade-offs in large-scale social media applications.

Contribution

It formulates the ranking problem as a QCQP that accounts for item interactions across slots and provides an efficient approximate solution algorithm.

Findings

Modeling item interactions improves ranking quality.

The proposed solver outperforms state-of-the-art methods in speed and accuracy.

The approach effectively balances multiple objectives in recommendation ranking.

Abstract

Ranking items to be recommended to users is one of the main problems in large scale social media applications. This problem can be set up as a multi-objective optimization problem to allow for trading off multiple, potentially conflicting objectives (that are driven by those items) against each other. Most previous approaches to this problem optimize for a single slot without considering the interaction effect of these items on one another. In this paper, we develop a constrained multi-slot optimization formulation, which allows for modeling interactions among the items on the different slots. We characterize the solution in terms of problem parameters and identify conditions under which an efficient solution is possible. The problem formulation results in a quadratically constrained quadratic program (QCQP). We provide an algorithm that gives us an efficient solution by relaxing the constraints of the QCQP minimally. Through simulated experiments, we show the benefits of modeling interactions in a multi-slot ranking context, and the speed and accuracy of our QCQP approximate solver against other state of the art methods.