ABSTRACT
As machine learning based predictive systems pervade many aspects of our lives, an inherent bias and unfairness surface from time to time in the form of mispredictions in various domains. Recidivism, the tendency of offenders to reoffend after release from prison on parole, is one such domain where one race-based sub-population has been found to be treated more harshly than others. Current practices have focused on eliminating race information from datasets to reduce the predictive bias. In contrast to this, we built Singular Race Models, a novel approach of segmenting the dataset based on race, to train and test single race-based models to increase prediction accuracy and reduce racially inspired bias by considering only one race at a time. We created Singular Race Models for four different crime categories and compared these with base models created using all crimes and all races. This modeling choice helped us increase accuracy and analyze race related discrimination. A three-layered artificial neural network was utilized to do the heavy weight-lifting of recidivism prediction. With the help of several suitable metrics, in this paper, we demonstrate the increase in predictive accuracy of these Singular Race Models in various crime categories and analyze the causes and the secondary effect on bias.
- US ACM. 2017. Public Policy Council and ACM Europe Policy Committee, 2017. Statement on algorithmic transparency and accountability. (25 May). (2017).Google Scholar
- Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias: There's software used across the country to predict future criminals. And it's biased against blacks. ProPublica (2016).Google Scholar
- Richard Berk. 2012. Criminal Justice Forecasts of Risk: a Machine Learning Approach. Springer-Verlag New York Inc. Google ScholarDigital Library
- Avinash Bhati and Caterina G Roman. 2014. Evaluating and Quantifying the Specific Deterrent Effects of DNA Databases. Evaluation review 38, 1 (2014), 68--93.Google Scholar
- Toon Calders and Sicco Verwer. 2010. Three naive Bayes approaches for discrimination-free classification. Data Mining and Knowledge Discovery 21, 2 (2010), 277--292. Google ScholarDigital Library
- Julia Dressel and Hany Farid. 2018. The accuracy, fairness, and limits of predicting recidivism. Science advances 4, 1 (2018), eaao5580.Google Scholar
- Matthew R Durose, Alexia D Cooper, and Howard N Snyder. {n. d.}. Recidivism of prisoners released in 30 states in 2005: Patterns from 2005 to 2010.Google Scholar
- Grant Duwe and KiDeuk Kim. 2017. 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 (2017), 570--600.Google ScholarCross Ref
- Anil K Jain, Jianchang Mao, and KM Mohiuddin. 1996. Artificial neural networks: A tutorial. Computer 3 (1996), 31--44. Google ScholarDigital Library
- Hyunzee Jung, Solveig Spjeldnes, and Hide Yamatani. 2010. Recidivism and survival time: Racial disparity among jail ex-inmates. Social Work Research 34, 3 (2010), 181--189.Google ScholarCross Ref
- Patrick A Langan and David J Levin. 2002. Recidivism of prisoners released in 1994. Fed. Sent. R. 15 (2002), 58.Google ScholarCross Ref
- Andy Liaw, Matthew Wiener, et al. 2002. Classification and regression by randomForest. R news 2, 3 (2002), 18--22.Google Scholar
- Osonde A Osoba and William Welser IV. 2017. An intelligence in our image: The risks of bias and errors in artificial intelligence. Rand Corporation. Google ScholarDigital Library
- Turgut Ozkan. 2017. Predicting Recidivism Through Machine Learning. Ph.D. Dissertation.Google Scholar
- Robert E Schapire. 2013. Explaining adaboost. In Empirical inference. Springer, 37--52.Google Scholar
- Faye S Taxman, April Pattavina, Michael S Caudy, James Byrne, and Joseph Durso. 2013. The empirical basis for the RNR model with an updated RNR conceptual framework. In Simulation strategies to reduce recidivism. Springer, 73--111.Google Scholar
Index Terms
- Singular race models: addressing bias and accuracy in predicting prisoner recidivism
Recommendations
What are race conditions?: Some issues and formalizations
In shared-memory parallel programs that use explicit synchronization, race conditions result when accesses to shared memory are not properly synchronized. Race conditions are often considered to be manifestations of bugs, since their presence can cause ...
High-coverage, unbounded sound predictive race detection
PLDI 2018: Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and ImplementationDynamic program analysis can predict data races knowable from an observed execution, but existing predictive analyses either miss races or cannot analyze full program executions. This paper presents Vindicator, a novel, sound (no false races) predictive ...
Parallelizing data race detection
ASPLOS '13: Proceedings of the eighteenth international conference on Architectural support for programming languages and operating systemsDetecting data races in multithreaded programs is a crucial part of debugging such programs, but traditional data race detectors are too slow to use routinely. This paper shows how to speed up race detection by spreading the work across multiple cores. ...
Comments