TY - GEN
T1 - Algorithmic Bias in Recidivism Prediction
T2 - 34th AAAI Conference on Artificial Intelligence, AAAI 2020
AU - Khademi, Aria
AU - Honavar, Vasant
N1 - Publisher Copyright:
© 2020 The Twenty-Fifth AAAI/SIGAI Doctoral Consortium (AAAI-20). All Rights Reserved.
PY - 2020
Y1 - 2020
N2 - ProPublica's analysis of recidivism predictions produced by Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software tool for the task, has shown that the predictions were racially biased against African American defendants. We analyze the COMPAS data using a causal reformulation of the underlying algorithmic fairness problem. Specifically, we assess whether COMPAS exhibits racial bias against African American defendants using FACT, a recently introduced causality grounded measure of algorithmic fairness. We use the Neyman-Rubin potential outcomes framework for causal inference from observational data to estimate FACT from COMPAS data. Our analysis offers strong evidence that COMPAS exhibits racial bias against African American defendants. We further show that the FACT estimates from COMPAS data are robust in the presence of unmeasured confounding.
AB - ProPublica's analysis of recidivism predictions produced by Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software tool for the task, has shown that the predictions were racially biased against African American defendants. We analyze the COMPAS data using a causal reformulation of the underlying algorithmic fairness problem. Specifically, we assess whether COMPAS exhibits racial bias against African American defendants using FACT, a recently introduced causality grounded measure of algorithmic fairness. We use the Neyman-Rubin potential outcomes framework for causal inference from observational data to estimate FACT from COMPAS data. Our analysis offers strong evidence that COMPAS exhibits racial bias against African American defendants. We further show that the FACT estimates from COMPAS data are robust in the presence of unmeasured confounding.
UR - http://www.scopus.com/inward/record.url?scp=85106598872&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85106598872&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85106598872
T3 - AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
SP - 13839
EP - 13840
BT - AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
PB - AAAI press
Y2 - 7 February 2020 through 12 February 2020
ER -