IDEAS home Printed from
   My bibliography  Save this paper

Explainable Machine Learning for Predicting Homicide Clearance in the United States


  • Gian Maria Campedelli


Purpose: To explore the potential of Explainable Machine Learning in the prediction and detection of drivers of cleared homicides at the national- and state-levels in the United States. Methods: First, nine algorithmic approaches are compared to assess the best performance in predicting cleared homicides country-wise, using data from the Murder Accountability Project. The most accurate algorithm among all (XGBoost) is then used for predicting clearance outcomes state-wise. Second, SHAP, a framework for Explainable Artificial Intelligence, is employed to capture the most important features in explaining clearance patterns both at the national and state levels. Results: At the national level, XGBoost demonstrates to achieve the best performance overall. Substantial predictive variability is detected state-wise. In terms of explainability, SHAP highlights the relevance of several features in consistently predicting investigation outcomes. These include homicide circumstances, weapons, victims' sex and race, as well as number of involved offenders and victims. Conclusions: Explainable Machine Learning demonstrates to be a helpful framework for predicting homicide clearance. SHAP outcomes suggest a more organic integration of the two theoretical perspectives emerged in the literature. Furthermore, jurisdictional heterogeneity highlights the importance of developing ad hoc state-level strategies to improve police performance in clearing homicides.

Suggested Citation

  • Gian Maria Campedelli, 2022. "Explainable Machine Learning for Predicting Homicide Clearance in the United States," Papers 2203.04768,
  • Handle: RePEc:arx:papers:2203.04768

    Download full text from publisher

    File URL:
    File Function: Latest version
    Download Restriction: no

    References listed on IDEAS

    1. M. Marit Rehavi & Sonja B. Starr, 2014. "Racial Disparity in Federal Criminal Sentences," Journal of Political Economy, University of Chicago Press, vol. 122(6), pages 1320-1354.
    2. Papachristos, A.V. & Wildeman, C., 2014. "Network exposure and homicide victimization in an African American community," American Journal of Public Health, American Public Health Association, vol. 104(1), pages 143-150.
    3. Knox, Dean & Lowe, Will & Mummolo, Jonathan, 2020. "Administrative Records Mask Racially Biased Policing—CORRIGENDUM," American Political Science Review, Cambridge University Press, vol. 114(4), pages 1394-1394, November.
    4. Aaron Chalfin & Benjamin Hansen & Emily K. Weisburst & Morgan C. Williams, Jr., 2020. "Police Force Size and Civilian Race," NBER Working Papers 28202, National Bureau of Economic Research, Inc.
    5. Knox, Dean & Lowe, Will & Mummolo, Jonathan, 2020. "Administrative Records Mask Racially Biased Policing," American Political Science Review, Cambridge University Press, vol. 114(3), pages 619-637, August.
    6. Baskin, Deborah & Sommers, Ira, 2010. "The influence of forensic evidence on the case outcomes of homicide incidents," Journal of Criminal Justice, Elsevier, vol. 38(6), pages 1141-1149, November.
    7. Lee, Catherine, 2005. "The value of life in death: Multiple regression and event history analyses of homicide clearance in Los Angeles County," Journal of Criminal Justice, Elsevier, vol. 33(6), pages 527-534.
    8. Gian Maria Campedelli, 2021. "Where are we? Using Scopus to map the literature at the intersection between artificial intelligence and research on crime," Journal of Computational Social Science, Springer, vol. 4(2), pages 503-530, November.
    9. Emma Pierson & Camelia Simoiu & Jan Overgoor & Sam Corbett-Davies & Daniel Jenson & Amy Shoemaker & Vignesh Ramachandran & Phoebe Barghouty & Cheryl Phillips & Ravi Shroff & Sharad Goel, 2020. "A large-scale analysis of racial disparities in police stops across the United States," Nature Human Behaviour, Nature, vol. 4(7), pages 736-745, July.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Campedelli, Gian Maria, 2022. "Explainable machine learning for predicting homicide clearance in the United States," Journal of Criminal Justice, Elsevier, vol. 79(C).
    2. Federico Masera, 2022. "The economics of policing and crimeThe economics of policing and crime," Chapters, in: Paolo Buonanno & Paolo Vanin & Juan Vargas (ed.), A Modern Guide to the Economics of Crime, chapter 2, pages 12-29, Edward Elgar Publishing.
    3. Desmond Ang & Panka Bencsik & Jesse Bruhn & Ellora Derenoncourt, 2021. "Police violence reduces civilian cooperation and engagement with law enforcement," Working Papers 2021-005, Brown University, Department of Economics.
    4. Anuli Njoku & Marcelin Joseph & Rochelle Felix, 2021. "Changing the Narrative: Structural Barriers and Racial and Ethnic Inequities in COVID-19 Vaccination," IJERPH, MDPI, vol. 18(18), pages 1-14, September.
    5. Pradhi Aggarwal & Alec Brandon & Ariel Goldszmidt & Justin Holz & John List & Ian Muir & Gregory Sun & Thomas Yu, 2022. "High-frequency location data shows that race affects the likelihood of being stopped and fined for speeding," Natural Field Experiments 00764, The Field Experiments Website.
    6. Riley, Taylor & Schleimer, Julia P. & Jahn, Jaquelyn L., 2024. "Organized abandonment under racial capitalism: Measuring accountable actors of structural racism for public health research and action," Social Science & Medicine, Elsevier, vol. 343(C).
    7. Beauregard, Eric & Martineau, Melissa, 2014. "No body, no crime? The role of forensic awareness in avoiding police detection in cases of sexual homicide," Journal of Criminal Justice, Elsevier, vol. 42(2), pages 213-220.
    8. Kasy, Maximilian, 2024. "Algorithmic Bias and Racial Inequality: A Critical Review," IZA Discussion Papers 16944, Institute of Labor Economics (IZA).
    9. Nayoung Rim & Roman Rivera & Andrea Kiss & Bocar Ba, 2020. "The Black-White Recognition Gap in Award Nominations," Working Papers 2020-065, Human Capital and Economic Opportunity Working Group.
    10. Desmond Ang, 2021. "The Effects of Police Violence on Inner-City Students," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 136(1), pages 115-168.
    11. Desmond Ang & Panka Bencsik & Jesse Bruhn & Ellora Derenoncourt, 2023. "Shots Fired: Crime and Community Engagement with Law Enforcement after High-profile Acts of Police Violence," Working Papers 315, Princeton University, Department of Economics, Center for Economic Policy Studies..
    12. Brendan O'Flaherty & Rajiv Sethi & Morgan Williams, 2024. "The nature, detection, and avoidance of harmful discrimination in criminal justice," Journal of Policy Analysis and Management, John Wiley & Sons, Ltd., vol. 43(1), pages 289-320, January.
    13. Charles Crabtree & John B. Holbein & J. Quin Monson, 2022. "Patient traits shape health-care stakeholders’ choices on how to best allocate life-saving care," Nature Human Behaviour, Nature, vol. 6(2), pages 244-257, February.
    14. Quinn, Katherine G. & Edwards, Travonne & Johnson, Anthony & Takahashi, Lois & Dakin, Andrea & Bouacha, Nora & Voisin, Dexter, 2023. "Understanding the impact of police brutality on Black sexually minoritized men," Social Science & Medicine, Elsevier, vol. 334(C).
    15. Cécile Bourreau-Dubois & Myriam Doriat-Duban & Bruno Jeandidier & Jean-Claude Ray, 2023. "Do child support guidelines result in lower inter-judge disparity? The case of the French advisory child support guidelines," European Journal of Law and Economics, Springer, vol. 55(1), pages 87-116, February.
    16. Chen, Daniel L. & Prescott, J.J., 2016. "Implicit Egoism in Sentencing Decisions: First Letter Name Effects with Randomly Assigned Defendants," IAST Working Papers 16-56, Institute for Advanced Study in Toulouse (IAST).
    17. Simone Bertoli & Morgane Laouenan & Jérôme Valette, 2022. "Border Apprehensions and Federal Sentencing of Hispanic Citizens in the United States," SciencePo Working papers Main hal-03818735, HAL.
    18. Brigitte Pereira, 2023. "Guidelines, court decisions and dismissals [Barèmes d’indemnisation, décisions de justice et licenciement]," Post-Print hal-04190156, HAL.
    19. Cécile Bourreau-Dubois & Myriam Doriat-Duban & Bruno Jeandidier & Jean Claude Ray, 2020. "Do sentencing guidelines result in lower inter-judge disparity? Evidence from framed field experiment," Working Papers of BETA 2020-28, Bureau d'Economie Théorique et Appliquée, UDS, Strasbourg.
    20. Dasom Lee & David J. Hess, 2022. "Public concerns and connected and automated vehicles: safety, privacy, and data security," Palgrave Communications, Palgrave Macmillan, vol. 9(1), pages 1-13, December.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:


    Access and download statistics


    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2203.04768. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.