On the Within-Group Fairness of Screening Classifiers

Nastaran Okati, Stratis Tsirtsis, Manuel Gomez Rodriguez
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26495-26516, 2023.

Abstract

Screening classifiers are increasingly used to identify qualified candidates in a variety of selection processes. In this context, it has been recently shown that if a classifier is calibrated, one can identify the smallest set of candidates which contains, in expectation, a desired number of qualified candidates using a threshold decision rule. This lends support to focusing on calibration as the only requirement for screening classifiers. In this paper, we argue that screening policies that use calibrated classifiers may suffer from an understudied type of within-group unfairness—they may unfairly treat qualified members within demographic groups of interest. Further, we argue that this type of unfairness can be avoided if classifiers satisfy within-group monotonicity, a natural monotonicity property within each group. Then, we introduce an efficient post-processing algorithm based on dynamic programming to minimally modify a given calibrated classifier so that its probability estimates satisfy within-group monotonicity. We validate our algorithm using US Census survey data and show that within-group monotonicity can often be achieved at a small cost in terms of prediction granularity and shortlist size.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-okati23a, title = {On the Within-Group Fairness of Screening Classifiers}, author = {Okati, Nastaran and Tsirtsis, Stratis and Gomez Rodriguez, Manuel}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {26495--26516}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/okati23a/okati23a.pdf}, url = {https://proceedings.mlr.press/v202/okati23a.html}, abstract = {Screening classifiers are increasingly used to identify qualified candidates in a variety of selection processes. In this context, it has been recently shown that if a classifier is calibrated, one can identify the smallest set of candidates which contains, in expectation, a desired number of qualified candidates using a threshold decision rule. This lends support to focusing on calibration as the only requirement for screening classifiers. In this paper, we argue that screening policies that use calibrated classifiers may suffer from an understudied type of within-group unfairness—they may unfairly treat qualified members within demographic groups of interest. Further, we argue that this type of unfairness can be avoided if classifiers satisfy within-group monotonicity, a natural monotonicity property within each group. Then, we introduce an efficient post-processing algorithm based on dynamic programming to minimally modify a given calibrated classifier so that its probability estimates satisfy within-group monotonicity. We validate our algorithm using US Census survey data and show that within-group monotonicity can often be achieved at a small cost in terms of prediction granularity and shortlist size.} }
Endnote
%0 Conference Paper %T On the Within-Group Fairness of Screening Classifiers %A Nastaran Okati %A Stratis Tsirtsis %A Manuel Gomez Rodriguez %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-okati23a %I PMLR %P 26495--26516 %U https://proceedings.mlr.press/v202/okati23a.html %V 202 %X Screening classifiers are increasingly used to identify qualified candidates in a variety of selection processes. In this context, it has been recently shown that if a classifier is calibrated, one can identify the smallest set of candidates which contains, in expectation, a desired number of qualified candidates using a threshold decision rule. This lends support to focusing on calibration as the only requirement for screening classifiers. In this paper, we argue that screening policies that use calibrated classifiers may suffer from an understudied type of within-group unfairness—they may unfairly treat qualified members within demographic groups of interest. Further, we argue that this type of unfairness can be avoided if classifiers satisfy within-group monotonicity, a natural monotonicity property within each group. Then, we introduce an efficient post-processing algorithm based on dynamic programming to minimally modify a given calibrated classifier so that its probability estimates satisfy within-group monotonicity. We validate our algorithm using US Census survey data and show that within-group monotonicity can often be achieved at a small cost in terms of prediction granularity and shortlist size.
APA
Okati, N., Tsirtsis, S. & Gomez Rodriguez, M.. (2023). On the Within-Group Fairness of Screening Classifiers. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:26495-26516 Available from https://proceedings.mlr.press/v202/okati23a.html.

Related Material