Ranking with Long-Term Constraints

TL;DR

This paper introduces a new framework and algorithms for ranking systems that incorporate long-term constraints like fairness and revenue goals, balancing short-term engagement with long-term sustainability.

Contribution

It develops control-based algorithms that enable ranking systems to meet long-term goals expressed by decision makers, beyond immediate user engagement.

Findings

Controllers achieve long-term goals with minimal short-term impact

Algorithms demonstrate robustness and efficiency in synthetic and real data

Trade-offs exist between planning ability, robustness, and efficiency

Abstract

The feedback that users provide through their choices (e.g., clicks, purchases) is one of the most common types of data readily available for training search and recommendation algorithms. However, myopically training systems based on choice data may only improve short-term engagement, but not the long-term sustainability of the platform and the long-term benefits to its users, content providers, and other stakeholders. In this paper, we thus develop a new framework in which decision makers (e.g., platform operators, regulators, users) can express long-term goals for the behavior of the platform (e.g., fairness, revenue distribution, legal requirements). These goals take the form of exposure or impact targets that go well beyond individual sessions, and we provide new control-based algorithms to achieve these goals. In particular, the controllers are designed to achieve the stated long-term goals with minimum impact on short-term engagement. Beyond the principled theoretical derivation of the controllers, we evaluate the algorithms on both synthetic and real-world data. While all controllers perform well, we find that they provide interesting trade-offs in efficiency, robustness, and the ability to plan ahead.