Predicting Recidivism With Machine Learning: An Analysis of Risk Factors and Proposal of Preventions
DOI:
https://doi.org/10.47611/jsrhs.v12i4.5779Keywords:
Recidivism, Machine Learning, Decision Tree, Random Forest, Gradient Boosted Decision TreeAbstract
Despite efforts to support the re-entry of prisoners into society, a significant proportion of released offenders eventually return to crime. To identify areas for improvement within correctional facilities, researchers are directing their focus towards recidivism, the tendency of an offender to recommit a crime. Although past studies have identified factors that are correlated to recidivism, there is still uncertainty about the most significant combinations of factors that drive it. Due to the complexity of this issue, the goal of our project is to create a machine-learning model to predict whether an individual will relapse into crime. Such a model will help experts study the effectiveness of specific forms of punishment and develop personalized correctional programs to target individuals based on their recidivism risk factors. We applied the Decision Tree, Random Forest, and Gradient Boosted Decision Tree algorithms to classify a prisoner as likely to recidivate or not, tuning the hyperparameters to optimize accuracy. To evaluate our hypotheses, we analyzed the top nodes of our trees and confirmed several of our initial predictions. Furthermore, we found that an individual’s relative placement in their community, such as the percentage of individuals in their community with lower or equal education levels, was a significant predictor of recidivism. The results of this research may help law enforcement officers make more informed decisions about how to allocate their resources based on predictions of recidivism.
Downloads
References or Bibliography
Bales, W. D., & Mears, D. P. (2008). Inmate Social Ties and the Transition to Society. Journal of Research in Crime and Delinquency. https://doi.org/10.1177/0022427808317574
Bureau of Prisons. (2018). Annual determination of average cost of incarceration. Federal Register. https://www.federalregister.gov/documents/2018/04/30/2018-09062/annual-determination-of-average-cost-of-incarceration
Dressel, J., & Farid, H. (2018). The accuracy, fairness, and limits of predicting recidivism. Science Advances, 4(1). https://doi.org/10.1126/sciadv.aao5580
Duwe, G., & Kim, K. (2015). Out with the old and in with the new? an empirical comparison of supervised learning algorithms to predict recidivism. Criminal Justice Policy Review, 28(6), 570–600. https://doi.org/10.1177/0887403415604899
Fazel, S., Sjöstedt, G., Långström, N., & Grann, M. (2006). Risk Factors for Criminal Recidivism in Older Sexual Offenders. Sexual Abuse: A Journal of Research and Treatment, 18(2). https://doi.org/10.1007/s11194-006-9009-0.
Grieger, L., & Hosser, D. (2014). Which Risk Factors are Really Predictive?: An Analysis of Andrews and Bonta’s “Central Eight” Risk Factors for Recidivism in German Youth Correctional Facility Inmates. Criminal Justice and Behavior, 41(5), 613-634. doi:10.1177/0093854813511432
Håkansson, A., & Berglund, M. (2012). Risk factors for criminal recidivism - a prospective follow-up study in prisoners with substance abuse. BMC psychiatry, 12, 111. https://doi.org/10.1186/1471-244X-12-111
Kassem, G. L. (2017). The Effects of Employment on Recidivism Among Delinquent Juveniles (Master's thesis, East Tennessee State University). East Tennessee State University.
Korzh, A. (2022). ‘You have been punished in prison. And then when you are released, you are punished for life’: Post-incarceration barriers for women in Ukraine. International Sociology, 37(3), 373–390. https://doi.org/10.1177/02685809221084447
Koschmann, M. A., & Peterson, B. L. (2013a). Rethinking recidivism. Journal of Applied Social Science, 7(2), 188–207. https://doi.org/10.1177/1936724412467021
Mattiuzzo, M., (2019) Algorithms and Big Data: Considerations on Algorithmic Governance and its Consequences for Antitrust Analysis. Revista de Economia Contemporanea, 23 (02). https://doi.org/10.1590/198055272328
Moore, K. E., Stuewig, J. B., & Tangney, J. P. (2015). The effect of stigma on criminal offenders’ functioning: A longitudinal mediational model. Deviant Behavior, 37(2), 196–218. https://doi.org/10.1080/01639625.2014.1004035
Nader, J. (2021, May 19). Serving data justice when predicting recidivism. Data Society. https://datasociety.com/serving-data-justice-when-predicting-recidivism/
National Institute of Justice. Measuring recidivism. (2008, February 28). https://nij.ojp.gov/topics/articles/measuring-recidivism
Pogorzelski W, Wolff N, Pan KY, Blitz CL. Behavioral health problems, ex-offender reentry policies, and the "Second Chance Act". Am J Public Health. 2005 Oct;95(10):1718-24. doi: 10.2105/AJPH.2005.065805. Epub 2005 Aug 30. PMID: 16131635; PMCID: PMC1449426.
Quinsey, V. L., Harris, G. T., Rice, M. E., & Lalumière, M. L. (1993). Assessing Treatment Efficacy in Outcome Studies of Sex Offenders. Journal of Interpersonal Violence. https://doi.org/10.1177/088626093008004006
Scommegna P., (2012). U.S. Has World’s Highest Population Rate. Population Reference Bureau. https://www.prb.org/resources/u-s-has-worlds-highest-incarceration-rate/
Solbakken, L. E., & Wynn, R. (2022). Barriers and opportunities to accessing social support in the transition from community to prison: a qualitative interview study with incarcerated individuals in Northern Norway. BMC psychology, 10(1), 185. https://doi.org/10.1186/s40359-022-00895-5
Tobón, S. (2022). Do Better Prisons Reduce Recidivism? Evidence from a Prison Construction Program. The Review of Economics and Statistics, 104(6), 1256–1272. https://doi.org/10.1162/rest_a_01007
Tollenaar, N., & van der Heijden, P. G. M. (2013). Which method predicts recidivism best?: a comparison of statistical, machine learning and data mining predictive models. Journal of the Royal Statistical Society. Series A (Statistics in Society), 176(2), 565–584. http://www.jstor.org/stable/23355205
Travaini, G. V., Pacchioni, F., Bellumore, S., Bosia, M., & De Micco, F. (2022). Machine Learning and Criminal Justice: A Systematic Review of Advanced Methodology for Recidivism Risk Prediction. International journal of environmental research and public health, 19(17), 10594. https://doi.org/10.3390/ijerph191710594
Tripodi, S. J., Kim, J. S., & Bender, K. (2010). Is Employment Associated With Reduced Recidivism?: The Complex Relationship Between Employment and Crime. International Journal of Offender Therapy and Comparative Criminology, 54(5), 706–720. https://doi.org/10.1177/0306624X09342980
Visher, C. A., & Travis, J. (2003). Transitions from Prison to Community: Understanding Individual Pathways. Annual Review of Sociology. https://doi.org/10.1146/annurev.soc.29.010202.095931
Published
How to Cite
Issue
Section
Copyright (c) 2023 Vienna Li, Srinitha Sridharan, Sandeep Sethuraman; Georgios Avdis
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
