The purpose of the 2014 SAS Data Analytics Shootout problem was to study the effect of various seasonal, economic, demographic, and climatological conditions on crime rates in five large US cities (Atlanta, Chicago, Denver, Houston, and Sacramento). Hourly precinct-level crime records for seven different crime types were provided for each city for different time periods between 2005 and 2012. Demographic and social economic data for each city were also provided, based on census data. In addition, weather conditions, holidays, daylight savings time, and other related information were also provided for each city. Some specific questions were asked, including: Which crime types would experience an increase if daylight savings were to be implemented year-round? What would happen if there were no daylight savings? How would crime rate change by crime type in the year 2032 if the daily temperature were increased uniformly by 0.72oF, but all other variables were left unchanged?
We built and compared different models for each crime type in each city and provided answers to the asked questions. Ultimately, our report was chosen as the first-place winner from among 68 submissions from graduate student teams throughout the country. In this presentation, we will first present our work for the Shootout problem and then share some of our experiences as participants in this contest. Our work was greatly supported by many faculty members of the Department of Statistics at the University of Georgia.