City of Chicago and Allstate: Case Study in Predictive Analytics

by Michael Watson

Yesterday’s Chicago Tribune ran an article on how Allstate and the City of Chicago are combining existing data sets with predictive analytics to solve long-standing problems. These problems include how to best conduct restaurant inspections to minimize food-borne illness, how to inspect elevators to prevent problems, and which trees to trim to minimize damage after a storm.

This article highlights a trend in the field of analytics: creatively using data in new ways to solve old problems. This often involves using external data sets or using data that was being collected internally, but not used. Data mining and machine learning algorithms allow you to sort through this new data, determine what data is important, and help identify patterns.

The Tribune story does a nice job of explaining how this works: The team started with a large set of data and used machine learning to determine the variables that were most likely to predict a problem with a restaurant. The city of Chicago also released a research report on the project.

This kind of approach can solve all types of problems. We have seen it used to help companies better forecast financial performance or sales performance with available economic or demographic data, better predict machine failures based on sensor data from a machine, better predict transportation prices given market conditions, or better predict the items to show a customer on a eCommerce portal.

___________________________________________________________________

If you liked this blog post, check out more of our work, follow us on social media (Twitter, LinkedIn, and Facebook), or join us for our free monthly Academy webinars.