Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation

TL;DR

This paper introduces a novel estimator for policy evaluation in randomized trials of algorithmic resource allocation, leveraging retrospective participant reshuffling to improve accuracy and reduce variance.

Contribution

It presents a new estimator that uses retrospective reshuffling of participants to create counterfactual trials, enabling more accurate policy evaluation.

Findings

The estimator is unbiased and has lower variance than traditional methods.

Empirical results show improved estimation accuracy on synthetic and real data.

The approach allows for better policy assessment in resource-constrained settings.

Abstract

We consider the task of evaluating policies of algorithmic resource allocation through randomized controlled trials (RCTs). Such policies are tasked with optimizing the utilization of limited intervention resources, with the goal of maximizing the benefits derived. Evaluation of such allocation policies through RCTs proves difficult, notwithstanding the scale of the trial, because the individuals' outcomes are inextricably interlinked through resource constraints controlling the policy decisions. Our key contribution is to present a new estimator leveraging our proposed novel concept, that involves retrospective reshuffling of participants across experimental arms at the end of an RCT. We identify conditions under which such reassignments are permissible and can be leveraged to construct counterfactual trials, whose outcomes can be accurately ascertained, for free. We prove theoretically that such an estimator is more accurate than common estimators based on sample means -- we show that it returns an unbiased estimate and simultaneously reduces variance. We demonstrate the value of our approach through empirical experiments on synthetic, semi-synthetic as well as real case study data and show improved estimation accuracy across the board.