2026-09-21T14:32:05Zhttps://openrepository.aut.ac.nz/server/oai/requestoai:openrepository.aut.ac.nz:10292/132652026-08-25T21:23:02Zcom_10292_3col_10292_476
AUT Research Repository
advisor
Ryan, Matthew
advisor
Skov, Peer
author
Desilvestro, Adrian
2020-04-14T23:57:29Z
2020-04-14T23:57:29Z
2020
https://hdl.handle.net/10292/13265
ProPublica’s allegations, that an algorithmic tool used to predict re-offenders is “biased against blacks”, met a wave of criticism from the wider community. Researchers have since shown a trade-off between accuracy and fairness, concluding that the risk tool, COMPAS, was not inherently discriminatory. However, in light of ProPublica’s objections, a growing body of literature on assessing fairness in machine learning systems has taken flight. Performance criteria combine quantitative and qualitative elements, so users ‘preferences’ are hard to specify objectively. This study explores a Pareto frontier framework to illustrate the relative model (in)efficiencies that arise in Risk Prediction Instruments (RPIs). The research follows a logistic framework for estimating recidivism risk, and the design parameters include the choice of fairness constraints and the choice of a bin scoring system (the “bin number”). This dissertation presents three experiments where decision-makers can improve performance in their RPIs: (1) improving efficiency through a relaxed version of the constraint, (2) improving efficiency through ‘cost-free’ constraint implementation, and (3) improving efficiency through a revised scoring system.
en
Algorithmic Fairness
Accuracy-fairness Tradeoffs
Risk Prediction Instruments
Pareto-frontier Framework
Abstraction and Prediction Algorithms: A Harm-Reduction Framework
Dissertation
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
URL
https://openrepository.aut.ac.nz/bitstreams/006ea953-0d8a-4264-bfe9-a8ae52c12754/download
File
MD5
beebb6822cc6e8bf1e7f2f7dd514e348
936304
application/pdf
Dissertation [60pts] - Adrian Desilvestro.pdf
URL
https://openrepository.aut.ac.nz/bitstreams/7740412e-c172-48e8-ac45-f1042288d302/download
File
MD5
9c53a068aa11064adfa2a3da3ba9d2ce
91513
text/plain
Dissertation [60pts] - Adrian Desilvestro.pdf.txt