# A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasets

arXiv: https://arxiv.org/abs/2108.09098 · HTML: https://mlsanity.com/paper/2108.09098/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 20 Aug 2021.

## Builds on (most cited first, 8 of 8)

- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Improving fairness in machine learning systems: What do industry practitioners need?](https://mlsanity.com/paper/1812.05239/) (2018)
- [A comparative study of fairness-enhancing interventions in machine learning](https://mlsanity.com/paper/1802.04422/) (2018)
- [On the Apparent Conflict Between Individual and Group Fairness](https://mlsanity.com/paper/1912.06883/) (2019)
- [Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns](https://mlsanity.com/paper/1906.03843/) (2019)

## Built on by (most cited first, 5 of 5)

- [Towards detecting unanticipated bias in Large Language Models](https://mlsanity.com/paper/2404.02650/) (2024)
- [Modeling Implicit Bias with Fuzzy Cognitive Maps](https://mlsanity.com/paper/2112.12713/) (2021)
- [Prolog-based agnostic explanation module for structured pattern classification](https://mlsanity.com/paper/2112.12641/) (2021)
- [Forward Composition Propagation for Explainable Neural Reasoning](https://mlsanity.com/paper/2112.12717/) (2021)
- [Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps](https://mlsanity.com/paper/2305.09399/) (2023)

## Abstract (arXiv)

The need to measure bias encoded in tabular data that are used to solve pattern recognition problems is widely recognized by academia, legislators and enterprises alike. In previous work, we proposed a bias quantification measure, called fuzzy-rough uncer-tainty, which relies on the fuzzy-rough set theory. The intuition dictates that protected features should not change the fuzzy-rough boundary regions of a decision class significantly. The extent to which this happens is a proxy for bias expressed as uncertainty in adecision-making context. Our measure's main advantage is that it does not depend on any machine learning prediction model but adistance function. In this paper, we extend our study by exploring the existence of bias encoded implicitly in non-protected featuresas defined by the correlation between protected and unprotected attributes. This analysis leads to four scenarios that domain experts should evaluate before deciding how to tackle bias. In addition, we conduct a sensitivity analysis to determine the fuzzy operatorsand distance function that best capture change in the boundary regions.