The Real-Time Crime Forecasting Challenge seeks to harness the advances in data science to address the challenges of crime and justice. It encourages data scientists across all scientific disciplines to foster innovation in forecasting methods. The goal is to develop algorithms that advance place-based crime forecasting through the use of data from one police jurisdiction.
The National Institute of Justice's (NIJ) Real-Time Crime Forecasting Challenge (the Challenge) hopes to provide researchers and the federal government with a better understanding of the potential for crime forecasting in America. This Challenge will offer a comprehensive comparative analysis between current "off-the-shelf" crime forecasting products used by many police departments and more innovative forecasting methods used by other scientific disciplines.
This Challenge is issued pursuant to 28 U.S.C. 530C.
As an interdisciplinary research arm of the U.S. Department of Justice, NIJ invests in scientific research across disciplines to serve the needs of the criminal justice community. NIJ recognizes that rapid advances in data sciences are being used to forecast consumer behavior, detect medical anomalies, and provide informatics about product consumers. These advances have been made by students, professors, scientists, corporations, and individuals across the spectrum of scientific disciplines, including biology, cognitive behavioral research, economics, and statistics. NIJ seeks innovative crime forecasting methods through the participation of data scientists from a wide range of scientific fields. By taking innovative ideas from various branches of science, NIJ hopes to inspire researchers and thinkers to discover ways that their own scientific pursuits might be used to help solve some of the criminal justice community's most vexing problems.
With this Challenge, NIJ aims to:
Accordingly, the Challenge will have three categories of contestants: students; individuals/small businesses; and large businesses. NIJ will evaluate all entries for both effectiveness and efficiency.
This Challenge will be based on the locations listed in calls-for-service (CFS) records provided by the Portland Police Bureau (PPB) for the period of March 1, 2012 through February 28, 2017. NIJ will initially release data for the period of March 1, 2012 through July 31, 2016, and NIJ will then release updated PPB's CFS data over a six-month period. During the final week of the six-month data rollout, contestants will submit forecasts of where the largest concentrations of crimes will occur within the PPB jurisdiction. The four crime categories are: all calls-for-service; burglary (residential and commercial); street crime; and motor vehicle theft. Contestants may submit forecasts for all or some of these categories. Crime forecasts can be submitted for each crime category for periods of one week, two weeks, one month, two months, and three months.
Contestants should be aware that other entities may make other data available through free or fee-based services (e.g., cloud and data sharing sites) that may or may not also be useful in developing their algorithms. Contestants are permitted, but not required, to use any other data sets or services.
After the PPB CFS data are collected for March 1, 2017, through May 31, 2017, NIJ will compare the Challenge entries to the actual data for each crime category and each designated time period, and will determine the effectiveness and efficiency index values. The most effective and the most efficient entries for each crime category, time period, and contestant type will be declared the Challenge winners. Contestants may win for more than one crime category and time period.
NIJ may award a total Challenge prize of up to $1,200,000.
On this page you will find:
To find out all this information, click here.