# Ex-Ante Assessment of Discrimination in Dataset

arXiv: https://arxiv.org/abs/2208.07918 · HTML: https://mlsanity.com/paper/2208.07918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 16 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [Why Is My Classifier Discriminatory?](https://mlsanity.com/paper/1805.12002/) (2018)
- [Algorithmic Fairness](https://mlsanity.com/paper/2001.09784/) (2020)
- [Runaway Feedback Loops in Predictive Policing](https://mlsanity.com/paper/1706.09847/) (2017)
- [An Empirical Study of Rich Subgroup Fairness for Machine Learning](https://mlsanity.com/paper/1808.08166/) (2018)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [Metric Learning for Individual Fairness](https://mlsanity.com/paper/1906.00250/) (2019)
- [Algorithmic Fairness in Education](https://mlsanity.com/paper/2007.05443/) (2020)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [Crowd, Lending, Machine, and Bias](https://mlsanity.com/paper/2008.04068/) (2020)
- [A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms](https://mlsanity.com/paper/2204.10233/) (2022)
- [Fair Representations by Compression](https://mlsanity.com/paper/2105.14044/) (2021)
- [Prescriptive and Descriptive Approaches to Machine-Learning Transparency](https://mlsanity.com/paper/2204.13582/) (2022)
- [Impact of Data Processing on Fairness in Supervised Learning](https://mlsanity.com/paper/2102.01867/) (2021)
- [Multi-Differential Fairness Auditor for Black Box Classifiers](https://mlsanity.com/paper/1903.07609/) (2019)

## Abstract (arXiv)

Data owners face increasing liability for how the use of their data could harm under-priviliged communities. Stakeholders would like to identify the characteristics of data that lead to algorithms being biased against any particular demographic groups, for example, defined by their race, gender, age, and/or religion. Specifically, we are interested in identifying subsets of the feature space where the ground truth response function from features to observed outcomes differs across demographic groups. To this end, we propose FORESEE, a FORESt of decision trEEs algorithm, which generates a score that captures how likely an individual's response varies with sensitive attributes. Empirically, we find that our approach allows us to identify the individuals who are most likely to be misclassified by several classifiers, including Random Forest, Logistic Regression, Support Vector Machine, and k-Nearest Neighbors. The advantage of our approach is that it allows stakeholders to characterize risky samples that may contribute to discrimination, as well as, use the FORESEE to estimate the risk of upcoming samples.