# Fairness Implications of Encoding Protected Categorical Attributes

arXiv: https://arxiv.org/abs/2201.11358 · HTML: https://mlsanity.com/paper/2201.11358/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 89 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 28 of 28)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [CatBoost: gradient boosting with categorical features support](https://mlsanity.com/paper/1810.11363/) (2018)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [Wasserstein Fair Classification](https://mlsanity.com/paper/1907.12059/) (2019)
- [An Intersectional Definition of Fairness](https://mlsanity.com/paper/1807.08362/) (2018)
- [An Empirical Study of Rich Subgroup Fairness for Machine Learning](https://mlsanity.com/paper/1808.08166/) (2018)
- [Explainable AI for Trees: From Local Explanations to Global Understanding](https://mlsanity.com/paper/1905.04610/) (2019)
- [From Parity to Preference-based Notions of Fairness in Classification](https://mlsanity.com/paper/1707.00010/) (2017)
- [Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation](https://mlsanity.com/paper/2004.08945/) (2020)
- [Beyond One-hot Encoding: lower dimensional target embedding](https://mlsanity.com/paper/1806.10805/) (2018)
- [Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness](https://mlsanity.com/paper/2010.05434/) (2020)
- [Similarity encoding for learning with dirty categorical variables](https://mlsanity.com/paper/1806.00979/) (2018)
- [POTs: Protective Optimization Technologies](https://mlsanity.com/paper/1806.02711/) (2018)
- [Bayesian Modeling of Intersectional Fairness: The Variance of Bias](https://mlsanity.com/paper/1811.07255/) (2018)
- [Encoding high-cardinality string categorical variables](https://mlsanity.com/paper/1907.01860/) (2019)
- [Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features](https://mlsanity.com/paper/2104.00629/) (2021)
- [Encoding Categorical Variables with Conjugate Bayesian Models for WeWork Lead Scoring Engine](https://mlsanity.com/paper/1904.13001/) (2019)
- [Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems](https://mlsanity.com/paper/2105.13783/) (2021)
- [Desiderata for Explainable AI in statistical production systems of the European Central Bank](https://mlsanity.com/paper/2107.08045/) (2021)

## Built on by (most cited first, 7 of 7)

- [Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness](https://mlsanity.com/paper/2303.17555/) (2023)
- [Multi-dimensional discrimination in Law and Machine Learning -- A comparative overview](https://mlsanity.com/paper/2302.05995/) (2023)
- [Lazy Data Practices Harm Fairness Research](https://mlsanity.com/paper/2404.17293/) (2024)
- [Encoding categorical data: Is there yet anything 'hotter' than one-hot encoding?](https://mlsanity.com/paper/2312.16930/) (2023)
- [Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measures](https://mlsanity.com/paper/2206.10043/) (2022)
- [Introducing explainable supervised machine learning into interactive feedback loops for statistical production system](https://mlsanity.com/paper/2202.03212/) (2022)
- [Design Principles of Robust Multi-Armed Bandit Framework in Video Recommendations](https://mlsanity.com/paper/2310.01419/) (2023)

## Abstract (arXiv)

Past research has demonstrated that the explicit use of protected attributes in machine learning can improve both performance and fairness. Many machine learning algorithms, however, cannot directly process categorical attributes, such as country of birth or ethnicity. Because protected attributes frequently are categorical, they must be encoded as features that can be input to a chosen machine learning algorithm, e.g. support vector machines, gradient boosting decision trees or linear models. Thereby, encoding methods influence how and what the machine learning algorithm will learn, affecting model performance and fairness. This work compares the accuracy and fairness implications of the two most well-known encoding methods: one-hot encoding and target encoding. We distinguish between two types of induced bias that may arise from these encoding methods and may lead to unfair models. The first type, textitirreducible bias, is due to direct group category discrimination, and the second type, textitreducible bias, is due to the large variance in statistically underrepresented groups. We investigate the interaction between categorical encodings and target encoding regularization methods that reduce unfairness. Furthermore, we consider the problem of intersectional unfairness that may arise when machine learning best practices improve performance measures by encoding several categorical attributes into a high-cardinality feature.