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.

This paper reports the results of two randomized field experiments, each offering different populations of Chicago youth a supported summer job. The program consistently reduces violent-crime arrests, even after the summer, without improving employment, schooling, or other arrests; if anything, property crime increases over two to three years. Using a new machine learning method, we uncover heterogeneity in employment impacts that standard methods would miss, describe who benefits, and leverage the heterogeneity to explore mechanisms. We conclude that brief youth employment programs can generate important behavioral change, but for different outcomes, youth, and reasons than those most often considered in the literature.

To estimate treatment heterogeneity in two randomized controlled trials of a youth summer jobs program, we implement Wager and Athey's (2015) causal forest algorithm. We provide a step-by-step explanation targeted at applied researchers of how the algorithm predicts treatment effects based on observables. We then explore how useful the predicted heterogeneity is in practice by testing whether youth with larger predicted treatment effects actually respond more in a hold-out sample. Our application highlights some limitations of the causal forest, but it also suggests that the method can identify treatment heterogeneity for some outcomes that more standard interaction approaches would have missed.

Gun violence is the most pressing public safety problem in U.S. cities. We report results from a randomized controlled trial (N = 2,456) of a community-researcher partnership called the Rapid Employment and Development Initiative (READI) Chicago. The program offered an 18-month job alongside cognitive behavioral therapy and other social support. Both algorithmic and human referral methods identified men with strikingly high scope for gun violence reduction: for every 100 people in the control group, there were 11 shooting and homicide victimizations during the 20-month outcome period. Fifty-five percent of the treatment group started programming, comparable to take-up rates in programs for people facing far lower mortality risk. After 20 months, there is no statistically significant change in an index combining three measures of serious violence, the study’s primary outcome. Yet there are signs that this program model has promise. One of the three measures, shooting and homicide arrests, declined 65% (p = .13 after multiple-testing adjustment). Because shootings are so costly, READI generated estimated social savings between $182,000 and $916,000 per participant (p = .03), implying a benefit-cost ratio between 4:1 and 18:1. Moreover, participants referred by outreach workers—a prespecified subgroup—saw enormous declines in arrests and victimizations for shootings and homicides (79% and 43%, respectively) which remain statistically significant even after multiple-testing adjustments. These declines are concentrated among outreach referrals with higher predicted risk, suggesting that human and algorithmic targeting may work better together.

We present the results of three large-scale randomized controlled trials (RCTs) carried out in Chicago, testing interventions to reduce crime and dropout by changing the decision making of economically disadvantaged youth. We study a program called Becoming a Man (BAM), developed by the nonprofit Youth Guidance, in two RCTs implemented in 2009–2010 and 2013–2015. In the two studies participation in the program reduced total arrests during the intervention period by 28–35%, reduced violent-crime arrests by 45–50%, improved school engagement, and in the first study where we have follow-up data, increased graduation rates by 12–19%. The third RCT tested a program with partially overlapping components carried out in the Cook County Juvenile Temporary Detention Center (JTDC), which reduced readmission rates to the facility by 21%. These large behavioral responses combined with modest program costs imply benefit-cost ratios for these interventions from 5-to-1 up to 30-to-1 or more. Our data on mechanisms are not ideal, but we find no positive evidence that these effects are due to changes in emotional intelligence or social skills, self-control or “grit,” or a generic mentoring effect. We find suggestive support for the hypothesis that the programs work by helping youth slow down and reflect on whether their automatic thoughts and behaviors are well suited to the situation they are in, or whether the situation could be construed differently.