Accuracy and Fairness for Juvenile Justice Risk Assessments

@article{Berk2019AccuracyAF,
  title={Accuracy and Fairness for Juvenile Justice Risk Assessments},
  author={R. Berk},
  journal={Criminal Procedure eJournal},
  year={2019}
}
  • R. Berk
  • Published 2019
  • Economics
  • Criminal Procedure eJournal
Risk assessment algorithms used in criminal justice settings are often said to introduce “bias.” But such charges can conflate an algorithm's performance with bias in the data used to train the algorithm with bias in the actions undertaken with an algorithm's output. In this article, algorithms themselves are the focus. Tradeoffs between different kinds of fairness and between fairness and accuracy are illustrated using an algorithmic application to juvenile justice data. Given… Expand
Almost politically acceptable criminal justice risk assessment
TLDR
This paper describes and applies to data on 300,000 offenders a machine learning approach that responds to many of the most visible charges of "racial bias" regardless of whether such claims are true, and adjusts procedures to compensate. Expand
Efficiency and fairness in recurring data-driven risk assessments of violent recidivism
TLDR
This work considers sequential evaluations performed on jail inmates with a state-of-the-art risk assessment instrument, RisCanvi, and analyzes if this method leads to discriminatory outcomes across some characteristics, including disparate impact in the evaluation rates along nationality and age. Expand
In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction
TLDR
This work revisits the recidivism prediction problem using state-of-the-art tools from interpretable machine learning, and assessing the models for performance, interpretability, and fairness, and presents multiple models that beat existing risk assessments in performance. Expand
The Role of Accuracy in Algorithmic Process Fairness Across Multiple Domains
  • M. Albach, James R. Wright
  • Computer Science
  • EC
  • 2021
TLDR
It is shown that, in every domain, disagreements in fairness judgements can be largely explained by the assignments of properties to features, and that fairness jud judgement can be well predicted across domains by training the predictor using the property assignments from one domain's data and predicting in another. Expand
Enhancing a recidivism prediction tool with machine learning: effectiveness and algorithmic fairness
TLDR
Results show that this bias mitigation procedure can substantially reduce generalized false positive rate disparities across multiple groups, and it is proposed that ML-based criminal recidivism risk prediction should not be introduced without applying algorithmic bias mitigation procedures. Expand
Predicting Early Dropout: Calibration and Algorithmic Fairness Considerations
TLDR
This work develops a machine learning method to predict the risks of university dropout and underperformance and analyzes if this method leads to discriminatory outcomes for some sensitive groups in terms of prediction accuracy and error rates. Expand
Fairness in Machine Learning: A Survey
TLDR
An overview of the different schools of thought and approaches to mitigating (social) biases and increase fairness in the Machine Learning literature is provided, organises approaches into the widely accepted framework of pre-processing, in- processing, and post-processing methods, subcategorizing into a further 11 method areas. Expand
Legal and human rights issues of AI: Gaps, challenges and vulnerabilities
Abstract This article focusses on legal and human rights issues of artificial intelligence (AI) being discussed and debated, how they are being addressed, gaps and challenges, and affected humanExpand
Vulnerable Citizens: Will Co-production Make a Difference?
One of the presumed benefits of introducing co-production is that it will lead to a greater inclusion of citizens and vulnerable people in particular. The chapter assesses how realistic that is, byExpand
When Algorithmic Transparency Failed: Controversies Over Algorithm-Driven Content Curation in the South Korean Digital Environment
Content curation in contemporary digital platforms leverages both algorithmic decision making and human judgment. As much as algorithm has become an integral part of digital configurations, there areExpand
...
1
2
...

References

SHOWING 1-10 OF 97 REFERENCES
Fairness in Criminal Justice Risk Assessments: The State of the Art
Objectives: Discussions of fairness in criminal justice risk assessments typically lack conceptual precision. Rhetoric too often substitutes for careful analysis. In this article, we seek to clarifyExpand
A Meta-Analysis of Juvenile Justice Risk Assessment Instruments
Juvenile justice systems have widely adopted risk assessment instruments to support judicial and administrative decisions about sanctioning severity and restrictiveness of care. A little exploredExpand
Risk Assessment in Juvenile Justice: A Guidebook for Implementation
Juvenile Defender Center (NJDC) for their assistance with this project and consultation on various drafts of this Guide. Anyone may use the content of this publication as is for educational purposesExpand
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
TLDR
It is demonstrated that the criteria cannot all be simultaneously satisfied when recidivism prevalence differs across groups, and how disparate impact can arise when an RPI fails to satisfy the criterion of error rate balance. Expand
Criminal Justice Forecasts of Risk
  • R. Berk
  • Business, Computer Science
  • SpringerBriefs in Computer Science
  • 2012
TLDR
This chapter provides a general introduction to forecasting criminal behavior in criminal justice settings and is a book about forecasting whether an individual already in the custody of the criminal justice system will subsequently re-offend. Expand
Risk-Needs Assessment: Constitutional and Ethical Challenges
Across jurisdictions, the criminal justice system is enamored with the evidence-based practices movement. The idea is to utilize the best scientific data to identify and classify individuals based onExpand
Legal and Ethical Issues in the Prediction of Recidivism
Evidence-Based Sentencing and the Scientific Rationalization of Discrimination
This paper critiques, on legal and empirical grounds, the growing trend of basing criminal sentences on actuarial recidivism risk prediction instruments that include demographic and socioeconomicExpand
Algorithmic Decision Making and the Cost of Fairness
TLDR
This work reformulate algorithmic fairness as constrained optimization: the objective is to maximize public safety while satisfying formal fairness constraints designed to reduce racial disparities, and also to human decision makers carrying out structured decision rules. Expand
Impartial Predictive Modeling: Ensuring Fairness in Arbitrary Models
TLDR
This work provides a framework for impartiality by accounting for different perspectives on the data generating process and yields a set of impartial estimates that are applicable in a wide variety of situations and post-processing tools to correct estimates from arbitrary models. Expand
...
1
2
3
4
5
...