# Measuring Implicit Bias Using SHAP Feature Importance and Fuzzy Cognitive Maps

arXiv: https://arxiv.org/abs/2305.09399 · HTML: https://mlsanity.com/paper/2305.09399/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 16 May 2023.

## Builds on (most cited first, 7 of 7)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Fairness by Explicability and Adversarial SHAP Learning](https://mlsanity.com/paper/2003.05330/) (2020)
- [Measuring Unfairness through Game-Theoretic Interpretability](https://mlsanity.com/paper/1910.05591/) (2019)
- [A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasets](https://mlsanity.com/paper/2108.09098/) (2021)
- [Recurrence-Aware Long-Term Cognitive Network for Explainable Pattern Classification](https://mlsanity.com/paper/2107.03423/) (2021)
- [Modeling Implicit Bias with Fuzzy Cognitive Maps](https://mlsanity.com/paper/2112.12713/) (2021)

## Abstract (arXiv)

In this paper, we integrate the concepts of feature importance with implicit bias in the context of pattern classification. This is done by means of a three-step methodology that involves (i) building a classifier and tuning its hyperparameters, (ii) building a Fuzzy Cognitive Map model able to quantify implicit bias, and (iii) using the SHAP feature importance to active the neural concepts when performing simulations. The results using a real case study concerning fairness research support our two-fold hypothesis. On the one hand, it is illustrated the risks of using a feature importance method as an absolute tool to measure implicit bias. On the other hand, it is concluded that the amount of bias towards protected features might differ depending on whether the features are numerically or categorically encoded.