Hindsight Analysis of the Chicago Food Inspection Forecasting Model

Abstract

The Chicago Department of Public Health (CDPH) conducts routine food inspections of over 15,000 food establishments to ensure the health and safety of their patrons. In 2015, CDPH deployed a machine learning model to schedule inspections of establishments based on their likelihood to commit critical food code violations. The City of Chicago released the training data and source code for the model, allowing anyone to examine the model. We provide the first independent analysis of the model, the data, the predictor variables, the performance metrics, and the underlying assumptions. We present a summary of our findings, share lessons learned, and make recommendations to address some of the issues our analysis unearthed.