# Confident Feature Ranking

arXiv: https://arxiv.org/abs/2307.15361 · HTML: https://mlsanity.com/paper/2307.15361/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 78 references that are in the map.
- First posted on arXiv 28 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [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)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [Explainable AI for Trees: From Local Explanations to Global Understanding](https://mlsanity.com/paper/1905.04610/) (2019)
- [Rethinking Stability for Attribution-based Explanations](https://mlsanity.com/paper/2203.06877/) (2022)
- [Stakeholders in Explainable AI](https://mlsanity.com/paper/1810.00184/) (2018)
- [Robust and Stable Black Box Explanations](https://mlsanity.com/paper/2011.06169/) (2020)
- [A Survey on the Robustness of Feature Importance and Counterfactual Explanations](https://mlsanity.com/paper/2111.00358/) (2021)
- [Applications and Techniques for Fast Machine Learning in Science](https://mlsanity.com/paper/2110.13041/) (2021)
- [Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process](https://mlsanity.com/paper/2109.01433/) (2021)
- [Understanding Global Feature Contributions With Additive Importance Measures](https://mlsanity.com/paper/2004.00668/) (2020)
- [Uncertainty in Ranking](https://mlsanity.com/paper/2107.03459/) (2021)
- [Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach](https://mlsanity.com/paper/2111.09121/) (2021)
- [An improvement of Tukey's HSD with application to ranking institutions](https://mlsanity.com/paper/1708.02428/) (2017)
- [Ranking with Confidence for Large Scale Comparison Data](https://mlsanity.com/paper/2202.01670/) (2022)

## Built on by (most cited first, 6 of 6)

- [Prediction-Powered Ranking of Large Language Models](https://mlsanity.com/paper/2402.17826/) (2024)
- [Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse](https://mlsanity.com/paper/2410.22598/) (2024)
- [Statistical Significance of Feature Importance Rankings](https://mlsanity.com/paper/2401.15800/) (2024)
- [Quantifying Ranking Uncertainty in LLM Benchmarks](https://mlsanity.com/paper/2607.16259/) (2026)
- [Rank Confidence Sequences:Anytime-valid Leaderboards](https://mlsanity.com/paper/2609.32211/) (2026)
- [Top-k Feature Importance Ranking](https://mlsanity.com/paper/2509.15420/) (2025)

## Abstract (arXiv)

Machine learning models are widely applied in various fields. Stakeholders often use post-hoc feature importance methods to better understand the input features' contribution to the models' predictions. The interpretation of the importance values provided by these methods is frequently based on the relative order of the features (their ranking) rather than the importance values themselves. Since the order may be unstable, we present a framework for quantifying the uncertainty in global importance values. We propose a novel method for the post-hoc interpretation of feature importance values that is based on the framework and pairwise comparisons of the feature importance values. This method produces simultaneous confidence intervals for the features' ranks, which include the ``true'' (infinite sample) ranks with high probability, and enables the selection of the set of the top-k important features.