Public Safety Lab

 
 
 
 

Bringing data science to public safety

 
 
nyu_stacked_color.png
shutterstock_260476700.jpg

WHAT WE DO

The Public Safety Lab uses the tools of data science to promote cost-effective public safety, with an awareness of both resource and social costs. We work with communities and law enforcement agencies to design, implement, and test analytic solutions that meet jurisdictions’ needs.

 

Communities and agencies interested in working with the Public Safety Lab can contact us at publicsafetylab@nyu.edu.

shutterstock_681723346.jpg

WHO WE ARE

The Public Safety Lab coordinates the work of researchers across multiple disciplines and universities.

 
 

Anna Harvey

Director

Professor of Politics

Affiliated Professor of Law

New York University

Greg DeAngelo

Chief Data Scientist

Associate Professor of Economics

Claremont Graduate University

 
 

Affiliated Faculty

 

Sharad Goel

Assistant Professor of Management Science and Engineering

Assistant Professor of Computer Science

Stanford University

 

Wei Long

Assistant Professor of Economics

Tulane University

Daniel Neill

Associate Professor of Information Systems

Carnegie Mellon University

Visiting Professor of Urban Analytics

New York University

Ravi Shroff

Assistant Professor of Applied Statistics and Urban Informatics

New York University

 
 

Chris Dawes

Associate Professor of Politics

New York University

Sanford Gordon

Professor of Politics

Affiliated Professor of Law

New York University

Hye Young You

Assistant Professor of Politics

New York University

 
 

Public Safety Lab Data Science Team

 

Tinghao Li

M.S. in Data Science

Center for Data Science

New York University

Yurui Mu

M.S. in Data Science

Center for Data Science

New York University

Fu Shang

M.S. in Data Science

Center for Data Science

New York University

Liwei Song

M.S. in Data Science

Center for Data Science

New York University

 

Yueqiu Sun

M.S. in Data Science

Center for Data Science

New York University

Ruofan Wang

M.S. in Data Science

Center for Data Science

New York University

Tingyan Xiang

M.S. in Data Science

Center for Data Science

New York University

Xue Yang

M.S. in Data Science

Center for Data Science

New York University

 

Binqian Zeng

M.S. in Data Science

Center for Data Science

New York University

Wei Zhang

M.S. in Data Science

Center for Data Science

New York University

Yidi Zhang

M.S. in Data Science

Center for Data Science

New York University

 

Public Safety Lab Doctoral Students

 

Abraham Aldama

Ph.D. Student

Department of Politics

New York University

Antonella Bandiera

Ph.D. Student

Department of Politics

New York University

Ryan Fackler

Ph.D. and J.D. Student

Department of Economics

University of Pennsylvania

New York University School of Law

Nicholas Haas

Ph.D. Student

Department of Politics

New York University

Niklas Loynes

Ph.D. Student

Department of Politics

University of Manchester

Taylor Mattia

Ph.D. Student

Department of Politics

New York University

Mateo Vasquez

Ph.D. Student

Department of Politics

New York University

Stephanie Zonszein

Ph.D. Student

Department of Politics

New York University

shutterstock_547175098.jpg

Current Projects

911 Officer Safety Analytics

Officers responding to calls for service often face unknown yet knowable threats to their safety. Human-assigned call priority codes do not typically incorporate information stored in agencies' prior call and case records, information that is potentially relevant to officer safety. Working with a large urban policing agency, we are engaged in developing and testing an analytic that will predict risks to officer safety using the corpus of prior call and case data, search for predicted risk factors associated with incoming calls, and then push predicted risk factors to responding officers. 

Human Trafficking Analytics

Sex trafficking is a crime of extraordinary violence visited largely upon vulnerable girls and young women. Its frequency is likely seriously underestimated, given the isolation within which its victims are kept. We are supporting the development and implementation of a human trafficking analytic that predicts instances of trafficking from the corpus of online commercial sex ads and provider reviews, and pushes predicted risk scores to law enforcement agencies for validation, as well as an effort to enrich the predictive model using case-level and call-level data from a large urban policing agency.

911 Bias Reduction Analytics

Calls to 911 are assigned priority codes by 911 call takers; these codes determine the speed and nature of the police response. The discretion inherent in the process by which priority codes are assigned to calls raises concerns that like calls are being treated alike. Working with a large urban policing agency, we are developing and testing an analytic that will assign to incoming 911 calls priority codes that do not incorporate irrelevant and potentially biasing information unrelated to civilian or officer safety.

Crowdsourcing Public Safety

Community residents may often have valuable information about recently committed crimes, information that is never shared with their local policing agency. Working with a large urban police department, we are developing and piloting a mobile application that will allow the community to partner with the department to co-produce public safety. Through the app, criminal investigators will be able to communicate with civilians near the location and time of day of recently committed crimes, with the capacity to solicit and receive video, photographic, or textual information.

Criminal Defendant Analytics

Ensuring that criminal defendants are treated equally before the law is one of the most important imperatives of criminal justice institutions. It can be a challenging question to investigate empirically, however, due to data limitations and problems of causal inference. Working with the text of every opinion issued by New York State's appellate courts between 2003 and 2017, incident, arrest, plea, trial, and sentencing data sourced from New York State's Unified Court System, and demographic data on criminal defendants sourced from New York State's Department of Corrections, we are building predictive models of criminal trial and appeal dispositions.

Civil Asset Forfeiture Analytics

Civil asset forfeiture allows law enforcement agencies to seize property upon the suspicion of criminal activity. While the practice may deter some criminal activity, it may also divert agency resources away from other productive pursuits, and may impose economic costs unevenly. We are collecting data on the amounts and types of assets being seized and forfeited by state and local law enforcement agencies, whether forfeitures are contested, demographic data on the subjects of asset forfeiture, incident-level data on law enforcement behavior, and cross-state and within-state variation in civil asset forfeiture statutes. Using these data we are building predictive models of the incidence and effects of civil asset forfeiture.

911 Response Feedback Survey

Patrol officers spend most of their time responding to calls for service. Yet callers to 911 often don't observe the law enforcement response to or resolution of their calls, possibly contributing to perceptions that their calls did not receive the attention or effort they deserved. At the same time, law enforcement agencies generally don't observe community perceptions of their 911 call response. Working with a large urban policing agency, we are conducting a randomized controlled trial of a platform that pushes an SMS-based survey to recent 911 callers, asking them to provide feedback on their experience of the police response. 

Social Networks and Violent Crime

Recent work has suggested that violent criminal behavior is often perpetrated through closely knit social networks, networks that facilitate overlapping forms of crime often associated with high rates of gun violence (e.g. drugs, guns, sex trafficking). This work suggests that identifying social networks with the potential to either encourage or discourage violent criminal behavior may be a promising policing strategy. Working with two large urban police forces in South America, we are analyzing whether randomized police interventions delivered through socially central individuals can reduce participation in violent criminal activity.

Community Policing

Although "community policing" has become a popular catchphrase, little is known systematically about whether community policing can improve communities' trust in their local law enforcement agencies. Working with a large urban police force in South America, we are analyzing whether randomly assigned town hall meetings bringing together residents and officers to discuss policing strategies can improve trust in law enforcement. 

Domestic Violence Policing

Law enforcement agencies in developing countries often fail to appropriately respond to domestic violence complaints. Working with a state policing agency in India, we are conducting a randomized controlled trial of several interventions designed to increase the efficacy of the police response to domestic violence complaints, including randomized officer training in alternative dispute resolution and random assignment of paralegals to assist in case development.

Reducing Failure to Pay

Many drivers who receive traffic citations either fail to pay their fines on time, incurring additional penalties, or fail to pay their fines at all, putting their licenses at risk. Working with a regional highway patrol agency, we are using a natural experiment to assess whether a longer time to pay window and/or smaller fines can reduce late payment/failure to pay, particularly for lower income drivers, without increasing recidivism or the propensity to be involved in an accident.

911 Call Response Time

Estimating the effect of 911 call response time on the risk of civilian injury is typically confounded by the fact that more emergent calls are generally characterized by both higher risk and shorter response times. Working with a large urban policing agency, we are exploiting the random assignment of 911 call takers to calls as a means to estimate the causal effect of shorter response times on the risk of civilian and officer injury.  

shutterstock_630604613.jpg