# Mitigating Nonlinear Algorithmic Bias in Binary Classification

arXiv: https://arxiv.org/abs/2312.05429 · HTML: https://mlsanity.com/paper/2312.05429/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 9 Dec 2023.

## Builds on (most cited first, 9 of 9)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [Survey on Causal-based Machine Learning Fairness Notions](https://mlsanity.com/paper/2010.09553/) (2020)
- [Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data](https://mlsanity.com/paper/1809.02519/) (2018)
- [Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality](https://mlsanity.com/paper/1903.11719/) (2019)
- [Causal Discovery for Fairness](https://mlsanity.com/paper/2206.06685/) (2022)
- [Blackbox Post-Processing for Multiclass Fairness](https://mlsanity.com/paper/2201.04461/) (2022)
- [Detecting and Mitigating Algorithmic Bias in Binary Classification using Causal Modeling](https://mlsanity.com/paper/2310.12421/) (2023)

## Built on by (most cited first, 1 of 1)

- [Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling](https://mlsanity.com/paper/2501.07885/) (2025)

## Abstract (arXiv)

This paper proposes the use of causal modeling to detect and mitigate algorithmic bias that is nonlinear in the protected attribute. We provide a general overview of our approach. We use the German Credit data set, which is available for download from the UC Irvine Machine Learning Repository, to develop (1) a prediction model, which is treated as a black box, and (2) a causal model for bias mitigation. In this paper, we focus on age bias and the problem of binary classification. We show that the probability of getting correctly classified as "low risk" is lowest among young people. The probability increases with age nonlinearly. To incorporate the nonlinearity into the causal model, we introduce a higher order polynomial term. Based on the fitted causal model, the de-biased probability estimates are computed, showing improved fairness with little impact on overall classification accuracy. Causal modeling is intuitive and, hence, its use can enhance explicability and promotes trust among different stakeholders of AI.