DemOpts: Fairness corrections in COVID-19 case prediction models

TL;DR

This paper identifies racial bias in COVID-19 prediction models caused by biased data and introduces DemOpts, a novel de-biasing method that improves fairness across racial and ethnic groups.

Contribution

The paper presents DemOpts, a new de-biasing technique that enhances fairness in COVID-19 forecasting models trained on biased datasets.

Findings

DemOpts achieves better error parity than existing methods.

State of the art models show significant error differences across racial groups.

DemOpts reduces mean error disparities across racial and ethnic groups.

Abstract

COVID-19 forecasting models have been used to inform decision making around resource allocation and intervention decisions e.g., hospital beds or stay-at-home orders. State of the art deep learning models often use multimodal data such as mobility or socio-demographic data to enhance COVID-19 case prediction models. Nevertheless, related work has revealed under-reporting bias in COVID-19 cases as well as sampling bias in mobility data for certain minority racial and ethnic groups, which could in turn affect the fairness of the COVID-19 predictions along race labels. In this paper, we show that state of the art deep learning models output mean prediction errors that are significantly different across racial and ethnic groups; and which could, in turn, support unfair policy decisions. We also propose a novel de-biasing method, DemOpts, to increase the fairness of deep learning based forecasting models trained on potentially biased datasets. Our results show that DemOpts can achieve better error parity that other state of the art de-biasing approaches, thus effectively reducing the differences in the mean error distributions across more racial and ethnic groups.