Using Chicago police data, we train a machine learning model to predict the risk of being shot in the next 18 months. Out-of-sample accuracy is strikingly high. A central concern with using police data is “baking in” bias, or overestimating risk for groups likelier to interact with police conditional on behavior. Our predictions, however, accurately recover risk across demographic groups. Legal, ethical, and practical barriers should prevent using victimization predictions to target law enforcement. But using them to target social services could increase both the potential for interventions to reduce shootings and the available statistical power to detect those reductions.

Economists have become increasingly interested in studying the nature of production functions in social policy applications, with the goal of improving productivity. Traditionally models have assumed workers are homogenous inputs. However, in practice, substantial variability in productivity means the marginal productivity of labor depends substantially on which new workers are hired--which requires not an estimate of a causal effect, but rather a prediction. We demonstrate that there can be large social welfare gains from using machine learning tools to predict worker productivity, using data from two important applications - police hiring and teacher tenure decisions.