Chicago is a city with about three million people and more than 15,000 food establishments. However, only fewer than three dozen inspectors check annually the city’s entire lot.
It has been estimated that at least 15% of these establishments earn a critical violation. This can drastically increase the possibility that a restaurant may start or spread a foodborne illness. Thereby targeting food establishments with critical violations is a priority.
The implementation of a pilot program using a predictive analytics platform, managed to optimize food inspection processes in the city.
The program was conducted by the Chicago Department of Innovation and Technology (DoIT), along with the Department of Public Health (CDPH) and other research partnerships.
Data from food inspection reports, services and weather as well as community and crime information were collected to bolster the model.
In processing and analyzing the data, Chicago found several key predicting variables such as prior history of critical violations, possession of a tobacco and/or incidental alcohol consumption license, length of time at which a establishment has been operating, length of time since last inspection, location of establishments nearby garbage and sanitation complaints, nearby burglaries and three day average high temperature.
The use of this analytics-based procedure allowed the city to discover critical violations, on average, seven days earlier than if they had used the traditional inspection procedure.
The results have implications not only for Chicago, but for cities anywhere that wish to optimize inspections processes using advanced analytics.