Fetching the paper…

Reading the bibliography…

2019

Fair-by-design explainable models for prediction of recidivism

Soares, Eduardo, Angelov, Plamen

Original
PDF
Post on X

Understand

Recidivism prediction provides decision makers with an assessment of the likelihood that a criminal defendant will reoffend that can be used in pre-trial decision-making.

It can also be used for prediction of locations where crimes most occur, profiles that are more likely to commit violent crimes.
While such instruments are gaining increasing popularity, their use is controversial as they may present potential discriminatory bias in the risk assessment.
In this paper we propose a new fair-by-design approach to predict recidivism.

Fair-by-design explainable models for prediction of recidivism · Around

Built on

Spatial tessellations: concepts and applications of Voronoi diagrams
Original
Atsuyuki Okabe, Barry Boots, Kokichi Sugihara, and Sung Nok Chiu · 1910
Earlier work this paper cites.
False positives, false negatives, and false analyses: A rejoinder to machine bias: There’s software used across the country to predict future criminals. and it’s biased against blacks
Anthony W Flores, Kristin Bechtel, and Christopher T Lowenkamp · 2016
Earlier work this paper cites.
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
Alexandra Chouldechova · 2017
Earlier work this paper cites.

Similar

Interpretable classification models for recidivism prediction
Jiaming Zeng, Berk Ustun, and Cynthia Rudin · 2017
Cited alongside, same era.
The accuracy, fairness, and limits of predicting recidivism
Julia Dressel and Hany Farid · 2018
Cited alongside, same era.
Achieving fairness through adversarial learning: an application to recidivism prediction
Original
Christina Wadsworth, Francesca Vera, and Chris Piech · 2018
Cited alongside, same era.

Then

An algorithm for removing sensitive information: application to race-independent recidivism prediction
James E Johndrow, Kristian Lum, et al · 2019
Closest in time.
Empirical approach to Machine Learning
Plamen P Angelov and Xiaowei Gu · 2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…