NIJ Real-Time Forecasting Challenge

Determining the Ability of Computer Algorithms to Forecast Crime




Chris Tillery

The NIJ is hosting a Real-Time Forecasting Challenge in hopes of harnessing the power of data science used to develop forecasting algorithms to help improve policing practices. The Challenge will examine how efficiently and effectively a contestant's algorithm can forecast crime in Portland, Oregon, based on five years of calls-for-service data provided by the Portland Police Bureau. Each forecast can be for one of four crime categories and for one of five timeframes, allowing contestants some flexibility with their approach and judging will be based on effectiveness and efficiency of the forecast to the actual calls-for-service during the specified period.

You can access this resource online here.