What is the Profile of American Inmate Misconduct Perpetrators? A Machine Learning Analysis

  • F. M. de Oliveira Pontíficia Universidade Católica de Minas Gerais
  • M. de S. Balbino Pontifícia Universidade Católica de Minas Gerais / Centro Federal de Educação Tecnológica de Minas Gerais
  • L. E. Zárate Pontifícia Universidade Católica de Minas Gerais
  • C. N. Nobre Pontíficia Universidade Católica de Minas Gerais

Resumo


Correctional institutions often develop rehabilitation programs to reduce the likelihood of inmates committing internal offenses and criminal recidivism after release. Therefore, it is necessary to identify the profile of each offender, both for the appropriate indication of a rehabilitation program and the level of internal security to which he must be submitted. In this context, this work aims to discover, from Machine Learning methods and the SHAP approach, which are the most significant characteristics in the prediction of misconduct by prisoners. For this, a database produced in 2004 through the Survey of Inmates in State and Federal Correctional Facilities in the United States of America, which provides nationally representative data on prisoners in state and federal facilities, was used. The predictive model based on Random Forest had the best performance; therefore, SHAP was applied to it to interpret the results. In addition, the attributes related to the type of crime committed, age at first arrest, drug use, mental or emotional health problems, having children, and being abused before arrest are more relevant in predicting internal misconduct. Thus, it is expected to contribute to the prior classification of an inmate, on time, use of programs and practices that aim to improve the lives of offenders, their reintegration into society, and, consequently, the reduction of criminal recidivism.

Palavras-chave: Misconduct, Crime, Recidivism, Machine Learning, SHAP

Referências

Berk, R. A., Kriegler, B., and Baek, J. H. Forecasting dangerous inmate misconduct: An application of ensemble statistical procedures. Journal of Quantitative Criminology 22 (2): 131–145, 2006.

Chongmin, N., Gyeongseok, O., Juyoung, S., and Hyoungah, P. Do machine learning methods outperform traditional statistical models in crime prediction? a comparison between logistic regression and neural networks. Korean Journal of Policy Studies 36 (1): 1–13, 2021.

Cihan, A., Davidson, M., and Sorensen, J. Analyzing the heterogeneous nature of inmate behavior: Trajectories of prison misconduct. The Prison Journal 97 (4): 431–450, 2017.

Cihan, A. and Sorensen, J. R. Examining developmental patterns of prison misconduct: An integrated model approach. International Journal of Offender Therapy and Comparative Criminology 63 (14): 2406–2421, 2019. PMID: 31088194.

Craig, J. M. and Trulson, C. R. Continuity of the delinquent career behind bars: Predictors of violent misconduct among female delinquents. Aggression and Violent Behavior vol. 49, pp. 101301, 2019.

Duwe, G. The development and validation of a classification system predicting severe and frequent prison misconduct. The Prison Journal 100 (2): 173–200, 2020.

Dâmboeanu, C. and Nieuwbeerta, P. Importation and deprivation correlates of misconduct among romanian inmates. European Journal of Criminology 13 (3): 332–351, 2016.

García-Gomis, A., Villanueva, L., and Jara, P. Risk factors and youth recidivism prediction in general and property offenders. Psychiatry, Psychology and Law vol. 24, pp. 1–11, 11, 2016.

Houser, K. A., Belenko, S., and Brennan, P. K. The effects of mental health and substance abuse disorders on institutional misconduct among female inmates. Justice Quarterly 29 (6): 799–828, 2012.

Houser, K. A. and Welsh, W. Examining the association between co-occurring disorders and seriousness of misconduct by female prison inmates. Criminal Justice and Behavior 41 (5): 650–666, 2014.

Jiang, S. and Fisher-Giorlando, M. Inmate misconduct: A test of the deprivation, importation, and situational models. The Prison Journal 82 (3): 335–358, 2002.

Kuo, S.-Y. The effects of mental health and substance abuse/dependence disorders on prison misconduct among male inmates in taiwan. International Journal of Offender Therapy and Comparative Criminology 64 (9): 953–976, 2020. PMID: 31884841.

Leigey, M. E. Female institutional misconduct: A test of deprivation, importation, and gendered importation theories. The Prison Journal 99 (3): 343–362, 2019.

Lundberg, S. M. and Lee, S.-I. A unified approach to interpreting model predictions. In Proceedings of the 31st international conference on neural information processing systems. pp. 4768–4777, 2017.

Meade, B., Wasileski, G., and Hunter, A. The effects of victimization prior to prison on victimization, misconduct, and sanction severity during incarceration. Crime & Delinquency 67 (12): 1856–1878, 2021.

Ngo, F., Govindu, R., and Agarwal, A. Traditional regression methods versus the utility of machine learning techniques in forecasting inmate misconduct in the united states: An exploration of the prospects of the techniques. International Journal of Criminal Justice Sciences vol. 13, pp. 420–437, 06, 2019.

Ngo, F. T., Govindu, R., and Agarwal, A. Assessing the predictive utility of logistic regression, classification and regression tree, chi-squared automatic interaction detection, and neural network models in predicting inmate misconduct. American Journal of Criminal Justice 40 (1): 47–74, 2015.

Nguyen, H., Midgette, G., Loughran, T., and Zhang, Y. Random drug testing in prisons: Does a little testing go a long way? Criminology & Public Policy 20 (2): 329–349, 2021.

of Justice Statistics, U. S. B. Survey of inmates in state and federal correctional facilities, [united states], 2004, 2019.

Qayyum, S., Hafsa, S., and Dar, H. Survey of data mining techniques for crime detection. University of Sindh Journal of Information and Communication Technology (USJICT) 2 (1): 1–6, 2018.

Rowell-Cunsolo, T. L., Sampong, S. A., Befus, M., Mukherjee, D. V., and Larson, E. L. Predictors of illicit drug use among prisoners. Substance Use & Misuse 51 (2): 261–267, 2016. PMID: 26789438.

Severson, R. E. Gender differences in mental health, institutional misconduct, and disciplinary segregation. Criminal Justice and Behavior 46 (12): 1719–1737, 2019.

Shlafer, R., Duwe, G., and Hindt, L. Parents in prison and their minor children: Comparisons between state and national estimates. The Prison Journal 99 (3): 310–328, 2019.

Steiner, B. Measuring and explaining inmate misconduct. The Oxford handbook of prisons and imprisonment, 2018.

Steiner, B., Butler, H., and Ellison, J. Causes and correlates of prison inmate misconduct: A systematic review of the evidence. Journal of Criminal Justice vol. 42, pp. 462–470, 12, 2014.

Stekhoven, D. J. and Bühlmann, P. MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics 28 (1): 112–118, 10, 2011.

Swanson, C., Lee, C.-B., Sansone, F. A., and Tatum, K. M. Prisoners’ perceptions of father-child relationships and social support. American Journal of Criminal Justice 37 (3): 338–355, 2012.

Taylor, M. Improving in-prison rehabilitation programs. Legislative Analyst’s Office, 2017. Accesso: 29-03-2018.

Tewksbury, R., Connor, D., and Denney, A. Disciplinary infractions behind bars: An exploration of importation and deprivation theories. Criminal Justice Review vol. 39, pp. 201–218, 04, 2014.
Publicado
28/11/2022
DE OLIVEIRA, F. M.; BALBINO, M. de S.; ZÁRATE, L. E.; NOBRE, C. N.. What is the Profile of American Inmate Misconduct Perpetrators? A Machine Learning Analysis. In: SYMPOSIUM ON KNOWLEDGE DISCOVERY, MINING AND LEARNING (KDMILE), 10. , 2022, Campinas/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 34-41. ISSN 2763-8944. DOI: https://doi.org/10.5753/kdmile.2022.227777.