fairadapt: Causal Reasoning for Fair Data Preprocessing
Machine learning algorithms are useful for various prediction tasks, but they can also learn how to discriminate, based on gender, race or other sensitive attributes. This realization gave rise to the field of fair machine learning, which aims to recognize, quantify and ultimately mitigate such alg...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Foundation for Open Access Statistics
2024-09-01
|
| Series: | Journal of Statistical Software |
| Online Access: | https://www.jstatsoft.org/index.php/jss/article/view/4729 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846101678384742400 |
|---|---|
| author | Drago Plečko Nicolas Bennett Nicolai Meinshausen |
| author_facet | Drago Plečko Nicolas Bennett Nicolai Meinshausen |
| author_sort | Drago Plečko |
| collection | DOAJ |
| description |
Machine learning algorithms are useful for various prediction tasks, but they can also learn how to discriminate, based on gender, race or other sensitive attributes. This realization gave rise to the field of fair machine learning, which aims to recognize, quantify and ultimately mitigate such algorithmic bias. This manuscript describes the R package fairadapt, which implements a causal inference preprocessing method. By making use of a causal graphical model alongside the observed data, the method can be used to address hypothetical questions of the form "What would my salary have been, had I been of a different gender/race?". Such individual level counterfactual reasoning can help eliminate discrimination and help justify fair decisions. We also discuss appropriate relaxations which assume that certain causal pathways from the sensitive attribute to the outcome are not discriminatory.
|
| format | Article |
| id | doaj-art-1b2a436a9c2d459aaa1264125e4d8778 |
| institution | Kabale University |
| issn | 1548-7660 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Foundation for Open Access Statistics |
| record_format | Article |
| series | Journal of Statistical Software |
| spelling | doaj-art-1b2a436a9c2d459aaa1264125e4d87782024-12-29T00:12:42ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602024-09-01110110.18637/jss.v110.i04fairadapt: Causal Reasoning for Fair Data PreprocessingDrago Plečko0Nicolas Bennett1Nicolai Meinshausen2ETH ZürichETH ZürichETH Zürich Machine learning algorithms are useful for various prediction tasks, but they can also learn how to discriminate, based on gender, race or other sensitive attributes. This realization gave rise to the field of fair machine learning, which aims to recognize, quantify and ultimately mitigate such algorithmic bias. This manuscript describes the R package fairadapt, which implements a causal inference preprocessing method. By making use of a causal graphical model alongside the observed data, the method can be used to address hypothetical questions of the form "What would my salary have been, had I been of a different gender/race?". Such individual level counterfactual reasoning can help eliminate discrimination and help justify fair decisions. We also discuss appropriate relaxations which assume that certain causal pathways from the sensitive attribute to the outcome are not discriminatory. https://www.jstatsoft.org/index.php/jss/article/view/4729 |
| spellingShingle | Drago Plečko Nicolas Bennett Nicolai Meinshausen fairadapt: Causal Reasoning for Fair Data Preprocessing Journal of Statistical Software |
| title | fairadapt: Causal Reasoning for Fair Data Preprocessing |
| title_full | fairadapt: Causal Reasoning for Fair Data Preprocessing |
| title_fullStr | fairadapt: Causal Reasoning for Fair Data Preprocessing |
| title_full_unstemmed | fairadapt: Causal Reasoning for Fair Data Preprocessing |
| title_short | fairadapt: Causal Reasoning for Fair Data Preprocessing |
| title_sort | fairadapt causal reasoning for fair data preprocessing |
| url | https://www.jstatsoft.org/index.php/jss/article/view/4729 |
| work_keys_str_mv | AT dragoplecko fairadaptcausalreasoningforfairdatapreprocessing AT nicolasbennett fairadaptcausalreasoningforfairdatapreprocessing AT nicolaimeinshausen fairadaptcausalreasoningforfairdatapreprocessing |