Chicago continues to use the traditional approach to assigning inspections on the basis of risk classification of a restaurant while it refines its computer model. At present, the model looks at 24 variables to identify which are the strongest indicators of a potential problem. “For instance, fluctuations in weather that might cause ingredients to rot were more strongly correlated with failure than a restaurant’s location or a history of past violations,” said the Post.
An epidemiologist at the Centers for Disease Control told the Post the attempts to harness Big Data for food safety are a “relatively new phenomenon” with an unproven record but which “could be useful in some contexts.”