Verrey Jacob, Neyroud Peter, Sherman Lawrence, Ariel Barak
Institute of Criminology, University of Cambridge, Sidgwick Ave, Cambridge, CB3 9DA UK.
Benchmark Cambridge Ltd., Rectory Lane, Somersham, PE28 3EL UK.
Neural Comput Appl. 2025;37(26):21607-21657. doi: 10.1007/s00521-025-11478-x. Epub 2025 Aug 1.
This investigation explores whether machine learning can predict recidivism while addressing societal biases. To investigate this, we obtained conviction data from the UK's Police National Computer (PNC) on 346,685 records between January 1, 2000, and February 3, 2006 (His Majesty's Inspectorate of Constabulary in Use of the Police National Computer: An inspection of the ACRO Criminal Records Office. His Majesty's Inspectorate of Constabulary, Birmingham, https://assets-hmicfrs.justiceinspectorates.gov.uk/uploads/police-national-computer-use-acro-criminal-records-office.pdf, 2017). We generate twelve machine learning models-six to forecast general recidivism, and six to forecast violent recidivism-over a 3-year period, evaluated via fivefold cross-validation. Our best-performing models outperform the existing state-of-the-arts, receiving an area under curve (AUC) score of 0.8660 and 0.8375 for general and violent recidivism, respectively. Next, we construct a fairness scale that communicates the semantic and technical trade-offs associated with debiasing a criminal justice forecasting model. We use this scale to debias our best-performing models. Results indicate both models can achieve all five fairness definitions because the metrics measuring these definitions-the statistical range of recall, precision, positive rate, and error balance between demographics-indicate that these scores are within a one percentage point difference of each other. Deployment recommendations and implications are discussed. These include recommended safeguards against false positives, an explication of how these models addressed societal biases, and a case study illustrating how these models can improve existing criminal justice practices. That is, these models may help police identify fewer people in a way less impacted by structural bias while still reducing crime. A randomized control trial is proposed to test this illustrated case study, and further directions explored.
The online version contains supplementary material available at 10.1007/s00521-025-11478-x.
本研究探讨机器学习能否在解决社会偏见的同时预测累犯情况。为了对此进行调查，我们从英国警察国家计算机（PNC）获取了2000年1月1日至2006年2月3日期间346,685条记录的定罪数据（陛下警察监察局对警察国家计算机使用情况的检查：对ACRO刑事记录办公室的检查。陛下警察监察局，伯明翰，https://assets-hmicfrs.justiceinspectorates.gov.uk/uploads/police-national-computer-use-acro-criminal-records-office.pdf，2017）。我们生成了12个机器学习模型——6个用于预测一般累犯，6个用于预测暴力累犯——在3年时间内通过五折交叉验证进行评估。我们表现最佳的模型优于现有最先进的模型，一般累犯和暴力累犯的曲线下面积（AUC）得分分别为0.8660和0.8375。接下来，我们构建了一个公平性量表，该量表传达了与消除刑事司法预测模型偏差相关的语义和技术权衡。我们使用这个量表对表现最佳的模型进行去偏。结果表明，两个模型都能实现所有五个公平性定义，因为衡量这些定义的指标——召回率、精确率、阳性率的统计范围以及不同人口统计特征之间的误差平衡——表明这些分数彼此相差在一个百分点以内。讨论了部署建议和影响。这些建议包括针对误报的推荐保障措施、对这些模型如何解决社会偏见的解释，以及一个说明这些模型如何改进现有刑事司法实践情况的案例研究。也就是说，这些模型可能有助于警方以较少受结构性偏见影响的方式识别更少的人，同时仍能减少犯罪。建议进行一项随机对照试验来测试这个案例研究，并探索进一步的方向。
在线版本包含可在10.1007/s00521-025-11478-x获取的补充材料。
