# Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models

arXiv: https://arxiv.org/abs/1611.04967 · HTML: https://mlsanity.com/paper/1611.04967/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2016.

## Built on by (most cited first, 12 of 12)

- [Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations](https://mlsanity.com/paper/2106.12723/) (2021)
- [Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline](https://mlsanity.com/paper/2106.06054/) (2021)
- [NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification](https://mlsanity.com/paper/2112.13214/) (2021)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [Adaptive Fairness Improvement Based on Causality Analysis](https://mlsanity.com/paper/2209.07190/) (2022)
- [MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset](https://mlsanity.com/paper/2102.06761/) (2021)
- [Fairness in Multi-Task Learning via Wasserstein Barycenters](https://mlsanity.com/paper/2306.10155/) (2023)
- [TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination](https://mlsanity.com/paper/2208.11321/) (2022)
- [Explainable Artificial Intelligence (XAI) for Malware Analysis: A Survey of Techniques, Applications, and Open Challenges](https://mlsanity.com/paper/2409.13723/) (2024)
- [Transforming Feature Space to Interpret Machine Learning Models](https://mlsanity.com/paper/2104.04295/) (2021)
- [Parametric Fairness with Statistical Guarantees](https://mlsanity.com/paper/2310.20508/) (2023)
- [Discrimination-free Insurance Pricing with Privatized Sensitive Attributes](https://mlsanity.com/paper/2504.11775/) (2025)

## Abstract (arXiv)

Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an iterative procedure, based on orthogonal projection of input attributes, for enabling interpretability of black-box predictive models. Through our iterative procedure, one can quantify the relative dependence of a black-box model on its input attributes.The relative significance of the inputs to a predictive model can then be used to assess the fairness (or discriminatory extent) of such a model.