Identifying Police Officers at Risk of Adverse Events
The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Adverse events between police and the public, such as deadly shootings or instances of racial profiling, can cause serious or deadly harm, damage police legitimacy, and result in costly litigation. Evidence suggests these events can be prevented by targeting interventions based on an Early Intervention System (EIS) that flags police officers who are at a high risk for involvement in such adverse events. Today's EIS are not data-driven and typically rely on simple thresholds based entirely on expert intuition. In this paper, we describe our work with the Charlotte-Mecklenburg Police Department (CMPD) to develop a machine learning model to predict which officers are at risk for an adverse event. Our approach significantly outperforms CMPD's existing EIS, increasing true positives by ~12% and decreasing false positives by ~32%. Our work also sheds light on features related to officer characteristics, situational factors, and neighborhood factors that are predictive of adverse events. This work provides a starting point for police departments to take a comprehensive, data-driven approach to improve policing and reduce harm to both officers and members of the public.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The gaze of risk assessments can be turned from defendants to the actors and institutions that comprise the criminal justice system [21,34], enabling a more structural view of the system's operations.”
From The false promise of risk assessments: epistemic reform and the limits of fairness (2020) · cites this paper as [21]
In the citing paper
“Importantly, we included metrics at a certain percentage of the population (often referred to as metrics at k) because they are more commonly used in ML for public policy in order to specifically addresses real-world resource constraints [2,12,66].”
From It’s Just Not That Simple: An Empirical Study of the Accuracy-Explainability Trade-off in Machine Learning for Public Policy (2022) · cites this paper as [12]
In the citing paper
“These metrics were chosen because they reflect the performance measures typically used in ML for public policy [9,12,20,56].”
From It’s Just Not That Simple: An Empirical Study of the Accuracy-Explainability Trade-off in Machine Learning for Public Policy (2022) · cites this paper as [12]
In the citing paper
“We chose these classifiers because they are representative of the types of models commonly used in ML for public policy systems [9,12,20,56].”
From It’s Just Not That Simple: An Empirical Study of the Accuracy-Explainability Trade-off in Machine Learning for Public Policy (2022) · cites this paper as [12]
Citations
Cites
Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2788613 · Cited by 1,685
The United States Department of Justice
Fairlie, J. (1905) · Michigan Law Review · doi:10.2307/1273036 · Cited by 542
Neighborhood Context and Police Use of Force
Terrill, W., & Reisig, M. D. (2003) · Journal of Research in Crime and Delinquency · doi:10.1177/0022427803253800 · Cited by 518
Identifying situational predictors of police shootings using multivariate analysis
White, M. D. (2002) · Policing An International Journal · doi:10.1108/13639510210450659 · Cited by 81
Use of force in minority communities is related to police education, age, experience, and ethnicity
Chapman, C. (2011) · Police Practice and Research · doi:10.1080/15614263.2011.596711 · Cited by 77
Early Warning Systems: Responding to the Problem Police Officer
Walker, S., Alpert, G. P., & Kenney, D. J. (2001) · Cited by 72
(2024) · CQ Press eBooks · doi:10.4135/9781071920541.n114 · Cited by 65
White, M. D., & Kane, R. J. (2013) · Criminal Justice and Behavior · doi:10.1177/0093854813486269 · Cited by 59
Exploring the Impact of Police Officer Education Level on Allegations of Police Misconduct
Manis, J., Archbold, C. A., & Hassell, K. D. (2008) · International Journal of Police Science & Management · doi:10.1350/ijps.2008.10.4.102 · Cited by 55
Shjarback, J. A. (2015) · Policing · doi:10.1093/police/pav006 · Cited by 37
Research works printed but not linked: 6
- Davis R. C., 2003, Washington
- Fernandez M., 2015, New York Times
- Goldstein H., 1977, Ballinger Pub. Co
- Hyndman R. J., 2014, OTexts
- Jones N., 2014, Proactive policing and adolescent development among young, poor black men. New directions for child and adolescent development
- Shultz A., 2015, Early warning systems: What's new? what's working?
Cited by
The Ethics of Artificial Intelligence: Principles, Challenges, and Opportunities
Floridi, L. (2023) · doi:10.1093/oso/9780198883098.001.0001 · Cited by 507
How to Design AI for Social Good: Seven Essential Factors
Floridi, L., Cowls, J., King, T. C., & Taddeo, M. (2020) · Science and Engineering Ethics · doi:10.1007/s11948-020-00213-5 · Cited by 430
“…to game-theoretic models to prevent poaching (Fang et al. 2016); from online reinforcement learning to target HIV-education at homeless youths (Yadav et al. 2016a, b) to probabilistic models to prevent harmful policing (Carton et al. 2016) and support student retention (Lakkaraju et al. 2015).”
BackgroundMethodAlgorithmic bias: Senses, sources, solutions
Fazelpour, S., & Danks, D. (2021) · Philosophy Compass · doi:10.1111/phc3.12760 · Cited by 272
Data Science as Political Action: Grounding Data Science in a Politics of Justice
Green, B. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3658431 · Cited by 156
How to Design AI for Social Good: Seven Essential Factors
Floridi, L., Cowls, J., King, T. C., & Taddeo, M. (2021) · Philosophical Studies Series · doi:10.1007/978-3-030-81907-1_9 · Cited by 161
Metadata
- Authors
- Carton, S., Helsby, J., Joseph, K., Mahmud, A., Park, Y., Walsh, J., Cody, C., Patterson, C. E., Haynes, L., & Ghani, R.
- Affiliations
- University of Michigan (US)
- University of Chicago (US)
- Carnegie Mellon University (US)
- Princeton University (US)
- University of Arizona (US)
- Charlotte-Mecklenburg Police Department, Charlotte, NC, USA
- Venue
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2016-08-13
- Pages
- 67-76
- OpenAlex
- W2516651778
- Cited by
- 64
- References
- 15
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 7 · 2023: 25 · 2022: 7 · 2021: 4 · 2020: 8 · 2019: 4 · 2018: 3
- FWCI
- 22.91
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Funders
- Office of Science
- Topics
- Social Sciences › Political Science and International Relations › Policing Practices and Perceptions
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Law › Artificial Intelligence in Law
- Keywords
- early intervention systems, risk prediction, police shootings, racial profiling, police legitimacy, machine learning prediction models, situational factors, neighborhood factors
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Identifying Police Officers at Risk of Adverse Events. https://app.cochat.ai/papers/10.1145/2939672.2939698
- The paper
- Carton, S., Helsby, J., Joseph, K., Mahmud, A., Park, Y., Walsh, J., Cody, C., Patterson, C. E., Haynes, L., & Ghani, R. (2016). Identifying Police Officers at Risk of Adverse Events. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939698
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.