Fair Decision-Making for Food Inspections

TL;DR

This paper analyzes the fairness of predictive models used in Chicago restaurant inspections, revealing disparities based on inspectors and geography, and explores alternative methods to improve fairness and effectiveness.

Contribution

First analysis of fairness in a real-world food inspection model, highlighting disparities and proposing alternative training and scheduling methods to enhance fairness.

Findings

Model treats inspections unequally based on sanitarians

Geographic disparities affect model benefits

Alternative scheduling methods yield better fairness

Abstract

Data and algorithms are essential and complementary parts of a large-scale decision-making process. However, their injudicious use can lead to unforeseen consequences, as has been observed by researchers and activists alike in the recent past. In this paper, we revisit the application of predictive models by the Chicago Department of Public Health to schedule restaurant inspections and prioritize the detection of critical food code violations. We perform the first analysis of the model's fairness to the population served by the restaurants in terms of average time to find a critical violation. We find that the model treats inspections unequally based on the sanitarian who conducted the inspection and that, in turn, there are geographic disparities in the benefits of the model. We examine four alternate methods of model training and two alternative ways of scheduling using the model and find that the latter generate more desirable results. The challenges from this application point to important directions for future work around fairness with collective entities rather than individuals, the use of critical violations as a proxy, and the disconnect between fair classification and fairness in the dynamic scheduling system.