Machine Learning Can Predict Shooting Victimization Well Enough to Help Prevent It
This paper shows that shootings are predictable enough to be preventable. Using arrest and victimization records for almost 644,000 people from the Chicago Police Department, we train a machine learning model to predict the risk of being shot in the next 18 months. We address central concerns about police data and algorithmic bias by predicting shooting victimization rather than arrest, which we show accurately captures risk differences across demographic groups despite bias in the predictors. Out-of-sample accuracy is strikingly high: of the 500 people with the highest predicted risk, 13 percent are shot within 18 months, a rate 130 times higher than the average Chicagoan. Although Black male victims more often have enough police contact to generate predictions, those predictions are not, on average, inflated; the demographic composition of predicted and actual shooting victims is almost identical. There are legal, ethical, and practical barriers to using these predictions to target law enforcement. But using them to target social services could have enormous preventive benefits: predictive accuracy among the top 500 people justifies spending up to $123,500 per person for an intervention that could cut their risk of being shot in half.
We thank Jalon Arthur, Phil Cook, Jen Doleac, Leif Elsmo, Jens Ludwig, Doug Miller, Emily Nix, Andy Papachristos, Greg Ridgeway, Mark Saint, Pat Sharkey, Ravi Shroff, and Megan Stevenson for their input and feedback. We thank Xander Beberman for outstanding research assistance. We are grateful to the Chicago Police Department for making available the data upon which this analysis is based. This research builds on a predictive model the authors developed to identify men at high risk of future gun violence involvement for referral into READI Chicago, an experimental preventive social service intervention. The larger research effort around READI Chicago was made possible with support from the philanthropic community, including the Partnership for Safe and Peaceful Communities, JPMorgan Chase, and the Chicago Sports Alliance. All opinions and any errors are our own and do not necessarily reflect those of our funders or of the Chicago Police Department. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.