# Simulating Biases for Interpretable Fairness in Offline and Online Classifiers

arXiv: https://arxiv.org/abs/2507.10154 · HTML: https://mlsanity.com/paper/2507.10154/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (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)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [River: machine learning for streaming data in Python](https://mlsanity.com/paper/2012.04740/) (2020)
- [Fairlearn: Assessing and Improving Fairness of AI Systems](https://mlsanity.com/paper/2303.16626/) (2023)
- [Directional Bias Amplification](https://mlsanity.com/paper/2102.12594/) (2021)
- [shapiq: Shapley Interactions for Machine Learning](https://mlsanity.com/paper/2410.01649/) (2024)
- [Overwriting Pretrained Bias with Finetuning Data](https://mlsanity.com/paper/2303.06167/) (2023)
- [Intra-Processing Methods for Debiasing Neural Networks](https://mlsanity.com/paper/2006.08564/) (2020)

## Abstract (arXiv)

Predictive models often reinforce biases which were originally embedded in their training data, through skewed decisions. In such cases, mitigation methods are critical to ensure that, regardless of the prevailing disparities, model outcomes are adjusted to be fair. To assess this, datasets could be systematically generated with specific biases, to train machine learning classifiers. Then, predictive outcomes could aid in the understanding of this bias embedding process. Hence, an agent-based model (ABM), depicting a loan application process that represents various systemic biases across two demographic groups, was developed to produce synthetic datasets. Then, by applying classifiers trained on them to predict loan outcomes, we can assess how biased data leads to unfairness. This highlights a main contribution of this work: a framework for synthetic dataset generation with controllable bias injection. We also contribute with a novel explainability technique, which shows how mitigations affect the way classifiers leverage data features, via second-order Shapley values. In experiments, both offline and online learning approaches are employed. Mitigations are applied at different stages of the modelling pipeline, such as during pre-processing and in-processing.