Search results

Despite the enormous toll of gun violence in America, shockingly little is known about what works to reduce gun violence or the illegal gun markets that put guns in dangerous hands. Research suggests that a typical crime gun is likely to be involved in a series of transactions between its first legal purchase from a Federal Firearms Licensee (FFL) and its recovery by police. These intermediate exchanges are largely invisible to gun trace data systems and governmental regulatory bodies, and known only to those involved in or close to these underground gun markets. The hypothesis motivating this project is that substantial progress could be made in the near term in reducing gun involvement in violence through strategic law enforcement interventions against what are call underground gun markets - if only more was known about how such markets actually worked.

To that end, the goal of this project is to learn more about how underground markets supply guns to people at highest risk of using them in violent crimes, through a mixed-methods study in Chicago that collects and analyzes several unique new sources of qualitative and quantitative data.

To address the relative difficulty in predicting domestic violence incidents and effectively targeting resources, the University of Chicago Crime Lab and the New York Police Department (NYPD) collaborated to develop and test a machine learning-based statistical model to predict the risk of domestic violence victimization in New York City.

Phase 1 of the project was to develop a statistical model using machine learning techniques. NYPD administrative records dated between January 2006 and January 2017 were used as input data to build and refine the tool. Due to the lack of unique identifiers for victims in the records, the research team also used data from the Chicago Police Department to create a probabilistic record linkage toolkit (Name Match) to identify which records belonged to the same person within and across data sources.

In Phase 2, the researchers aimed to field test the tool's capability to identify individuals at risk of repeated domestic violence through a large-scale randomized control trial. Measuring the effects of regular home visits of high-priority individuals thought to be at risk of serious domestic assault, the test intended to compare the selections of individuals made by officers versus those predicted by the tool.

This collection contains only the machine learning code files (R and Python) created during secondary analysis, which have been released as a zipped package. Please refer to the Data Roadmap for instructions on how to obtain the original NYPD data. To access the Name Change algorithm and documentation, please visit the Github repository.