Predicting high-harm offending using machine learning: An application to outlaw motorcycle gangs

Photo of motorcycles
Abstract

Risk assessment tools are used widely in the criminal justice response to serious offenders. Despite growing recognition that certain outlaw motorcycle gang (OMCG) members and their clubs are likely to be involved in crime, particularly serious crime, this is not an area where risk assessment tools have been developed and validated.

The nature of offending by OMCGs, and policing responses to OMCGs, requires a novel approach to risk assessment. This study uses machine learning methods to develop a risk assessment tool to predict recorded high-harm offending. Results are compared with those of a model predicting any recorded offending.

The model predicted high-harm offending with a high degree of accuracy. Importantly, the tool appeared able to accurately identify offenders prior to the point of escalation. This has important implications for informing law enforcement responses.

References

URLs correct as at November 2021

Albanese JS 2008. Risk assessment in organized crime: Developing a market and product-based model to determine threat levels. Journal of Contemporary Criminal Justice 24(3): 263–273. https://doi.org/10.1177/1043986208318225

Australian Federal Police 2021. AFP-led Operation Ironside smashes organised crime. Media release, 8 June. https://www.afp.gov.au/news-media/media-releases/afp-led-operation-ironside-smashes-organised-crime

Barnes GC & Hyatt JM 2012Classifying adult probationers by forecasting future offending. https://nij.ojp.gov/library/publications/classifying-adult-probationers-forecasting-future-offending

Bennett Moses L & Chan J 2018. Algorithmic prediction in policing: Assumptions, evaluation, and accountability. Policing and Society 7: 806–822. https://doi.org/10.1080/10439463.2016.1253695

Berk R 2021. Artificial intelligence, predictive policing, and risk assessment for law enforcement. Annual Review of Criminology 4: 209–237. https://doi.org/10.1146/annurev-criminol-051520-012342

Berk R 2019. Machine learning risk assessments in criminal justice settings. New York: Springer. https://doi.org/10.1007/978-3-030-02272-3

Berk R 2013. Algorithmic criminology. Security Informatics 2(1): 1–14. https://doi.org/10.1186/2190-8532-2-5

Berk R & Bleich J 2014. Forecasts of violence to inform sentencing decisions. Journal of Quantitative Criminology 31(1): 79–96. https://doi.org/10.1007/s10940-013-9195-0

Berk R, Heidari H, Jabbari S, Kearns M & Roth A 2018. Fairness in criminal justice risk assessment: The state of the art. Sociological Methods & Research 50(1): 3–44. https://doi.org/10.1177/0049124118782533

Berk R, Sherman L, Barnes G, Kurtz E & Ahlman L 2009. Forecasting murder within a population of probationers and parolees: A high stakes application of statistical learning. Statistics in Society 172(1): 191–211. https://doi.org/10.1111/j.1467-985X.2008.00556.x

Berk R, Sorenson SB & Barnes G 2016. Forecasting domestic violence: A machine learning approach to help inform arraignment decisions. Journal of Empirical Legal Studies 13(1): 94–115. https://doi.org/10.1111/jels.12098

Bjørgo T 2019. Preventing organised crime originating from outlaw motorcycle clubs. Trends in Organized Crime 22: 84–122. https://doi.org/10.1007/s12117-017-9322-7

Blokland A, van Hout L, van der Leest W & Soudijn M 2019. Not your average biker: Criminal careers of members of Dutch outlaw motorcycle gangs. Trends in Organized Crime 22: 10–33. https://doi.org/10.1007/s12117-017-9303-x

Boland D et al. 2021. Effects of outlaw motorcycle gang membership and the support needs of former members. Trends & issues in crime and criminal justice no. 614. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti78078

Coglianese C & Lehr D 2017. Regulating by robot: Administrative decision making in the machine learning era. Georgetown Law Journal 105: 1147–1223. https://ssrn.com/abstract=2928293

Couronné R, Probst P & Boulesteix AL 2018. Random forest versus logistic regression: A large-scale benchmark experiment. BMC Bioinformatics 19(270): 1–14. https://doi.org/10.1186/s12859-018-2264-5

Cubitt TIC, Wooden KR & Roberts KA 2020. A machine learning analysis of serious misconduct among Australian police. Crime Science 9(22): 114. https://doi.org/10.1186/s40163-020-00133-6

Dowling C et al. 2021. The changing culture of outlaw motorcycle gangs in Australia. Trends & issues in crime and criminal justice no. 615. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti78054

Dowling C & Morgan A 2021. Criminal mobility of outlaw motorcycle gangs in Australia. Trends & issues in crime and criminal justice no. 619. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti04992

Grogger J, Gupta S, Ivandic R & Kirchmaier T 2021. Comparing conventional and machine-learning approaches to risk assessment in domestic abuse cases. Journal of Empirical Legal Studies 18(1): 90130. https://doi.org/10.1111/jels.12276

Hong H, Xiaoling G & Hua Y 2016. Variable selection using mean decrease accuracy and mean decrease Gini based on random forest. Paper presented at the 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS). https://doi.org/10.1109/ICSESS.2016.7883053

House PD & Neyroud PW 2018. Developing a crime harm index for Western Australia: The WACHI. Cambridge Journal of Evidence-Based Policing 2(1–2): 70–94. https://doi.org/10.1007/s41887-018-0022-6

Hughes CE, Chalmers J & Bright DA 2020. Exploring interrelationships between high-level drug trafficking and other serous and organised crime: An Australian study. Global Crime 21(1): 28–50. https://doi.org/10.1080/17440572.2019.1615895

Hyndman RJ & Anthanasopoulos G 2014. Forecasting: Principles and practice. Melbourne: Monash University

Klement C 2016. Outlaw biker affiliations and criminal involvement. European Journal of Criminology 13(4): 453–72. https://doi.org/10.1177/1477370815626460

Lauchs M, Bain A & Bell P 2015. Outlaw motorcycle gangs: A theoretical perspective. London: Palgrave Macmillan. https://doi.org/10.1057/9781137456298

McKay C 2019. Predicting risk in criminal justice procedure: Actuarial tools, algorithms, AI and judicial decision-making. Current Issues in Criminal Justice 32(1): 22–39. https://doi.org/10.1080/10345329.2019.1658694

McSherry B 2013. Throwing away the key: The ethics of risk assessment for preventative detention schemes. Psychiatry, Psychology and Law 21(5): 779–790. https://www.doi.org/10.1080/13218719.2014.893551

Monterosso S 2018. From bikers to savvy criminals. Outlaw motorcycle gangs in Australia: Implications for legislators and law enforcement. Crime, Law and Social Change 69(5): 681–701. https://doi.org/10.1007/s10611-018-9771-1

Morgan A, Dowling C & Voce I 2020. Australian outlaw motorcycle gang involvement in violent and organised crime. Trends & issues in crime and criminal justice no. 586. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti04282

Morgan A & Payne J 2021. Organised crime and criminal careers: Findings from an Australian sample. Trends & Issues in crime and criminal justice no. 637. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti78337

Ratcliffe JH & Kikuchi G 2019. Harm-focused offender triage and prioritisation: A Philadelphia case study. Policing: An International Journal 42(1): 59–73. https://doi.org/10.1108/PIJPSM-08-2018-0118

Ratcliffe JH, Strang SJ & Taylor RB 2014. Assessing the success factors of organized crime groups: Intelligence challenges for strategic thinking. Policing: An International Journal of Police Strategies and Management 37(1): 206–227. https://doi.org/10.1108/PIJPSM-03-2012-0095

Ridgeway G 2013. The pitfalls of prediction. National Institute of Justice Journal 271: 34–40. https://nij.ojp.gov/topics/articles/pitfalls-prediction

Stevenson M & Doleac JL 2021. Algorithmic risk assessment in the hands of humans. https://doi.org/10.2139/ssrn.3489440

United Nations Office on Drugs and Crime (UNODC) 2010. The globalisation of crime: A transnational organized crime threat assessment. Vienna: UNODC. https://www.unodc.org/unodc/en/data-and-analysis/tocta-2010.html

Voce I, Morgan A & Dowling C 2021. Early-career offending trajectories among outlaw motorcycle gang members. Trends & issues in crime and criminal justice no. 625. Canberra: Australian Institute of Criminology. https://doi.org/10.52922/ti78030

von Lampe K & Blokland A 2020. Outlaw motorcycle clubs and organized crime. Crime and Justice 49. https://doi.org/10.1086/708926

Zoutendijk AJ 2010. Organised crime threat assessments: A critical review. Crime, Law and Social Change 54: 63–86. https://doi.org/10.1007/s10611-010-9244-7