# Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models

arXiv: https://arxiv.org/abs/2502.07153 · HTML: https://mlsanity.com/paper/2502.07153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 22 of 22)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks](https://mlsanity.com/paper/2306.17844/) (2023)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [Benchmarking Deep Learning Interpretability in Time Series Predictions](https://mlsanity.com/paper/2010.13924/) (2020)
- [Benchmarking Attribution Methods with Relative Feature Importance](https://mlsanity.com/paper/1907.09701/) (2019)
- [Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations](https://mlsanity.com/paper/2206.01254/) (2022)
- [Synthetic Benchmarks for Scientific Research in Explainable Machine Learning](https://mlsanity.com/paper/2106.12543/) (2021)
- [Evaluation of post-hoc interpretability methods in time-series classification](https://mlsanity.com/paper/2202.05656/) (2022)
- [Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods](https://mlsanity.com/paper/1910.02065/) (2019)
- [Order in the Court: Explainable AI Methods Prone to Disagreement](https://mlsanity.com/paper/2105.03287/) (2021)
- [ferret: a Framework for Benchmarking Explainers on Transformers](https://mlsanity.com/paper/2208.01575/) (2022)
- [A Debiased MDI Feature Importance Measure for Random Forests](https://mlsanity.com/paper/1906.10845/) (2019)
- [Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement](https://mlsanity.com/paper/2211.08943/) (2022)
- [The impact of feature importance methods on the interpretation of defect classifiers](https://mlsanity.com/paper/2202.02389/) (2022)

## Abstract (arXiv)

In order to ensure the reliability of the explanations of machine learning models, it is crucial to establish their advantages and limits and in which case each of these methods outperform. However, the current understanding of when and how each method of explanation can be used is insufficient. To fill this gap, we perform a comprehensive empirical evaluation by synthesizing multiple datasets with the desired properties. Our main objective is to assess the quality of feature importance estimates provided by local explanation methods, which are used to explain predictions made by decision tree-based models. By analyzing the results obtained from synthetic datasets as well as publicly available binary classification datasets, we observe notable disparities in the magnitude and sign of the feature importance estimates generated by these methods. Moreover, we find that these estimates are sensitive to specific properties present in the data. Although some model hyper-parameters do not significantly influence feature importance assignment, it is important to recognize that each method of explanation has limitations in specific contexts. Our assessment highlights these limitations and provides valuable insight into the suitability and reliability of different explanatory methods in various scenarios.