Reducing race-based bias and increasing recidivism prediction accuracy by using past criminal history details
| Autor: | Leonidas Fegaras, Bhanu Jain, Ramez Elmasri, Manfred Huber |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
021110 strategic
defence & security studies Decision support system Recidivism Artificial neural network Computer science business.industry media_common.quotation_subject Deep learning 0211 other engineering and technologies Prison 02 engineering and technology 01 natural sciences 010104 statistics & probability Race (biology) Statistics False positive rate Artificial intelligence 0101 mathematics business Diversity (business) media_common |
| Zdroj: | PETRA |
| DOI: | 10.1145/3389189.3397990 |
| Popis: | Recidivism, the propensity of convicts to reoffend after release from prison on parole, is a domain that has both benefited from machine learning based decision support systems and experienced race-based bias in the predictions. In this paper we propose an approach to select a model to increase recidivism prediction accuracy while reducing race-based bias. We built several models that each use offenders' current arrest's criminal information and accrue past criminal history information based on different numbers of prior arrests cycles. We then monitor accuracy and inherent bias in the results for different sub-populations. Finally, from the various criminal history-based models developed, we select the one that offers minimal bias for different subpopulations while increasing the accuracy by using False Positive Rate Parity. The approach allows adaptation to the diversity in training data, different crime types, and varied length of prior arrest cycle history. We assessed model prediction performance using ten independent iterations of Monte Carlo cross-validation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|