# On the Trustworthiness of Tree Ensemble Explainability Methods

arXiv: https://arxiv.org/abs/2110.00086 · HTML: https://mlsanity.com/paper/2110.00086/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 30 Sep 2021.

## Builds on (most cited first, 12 of 12)

- [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)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [A Random Forest Guided Tour](https://mlsanity.com/paper/1511.05741/) (2015)
- [Variable Importance Clouds: A Way to Explore Variable Importance for the Set of Good Models](https://mlsanity.com/paper/1901.03209/) (2019)
- [Limitations and Biases in Facial Landmark Detection -- An Empirical Study on Older Adults with Dementia](https://mlsanity.com/paper/1905.07446/) (2019)
- [A Hybrid Instance-based Transfer Learning Method](https://mlsanity.com/paper/1812.01063/) (2018)

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

- [A Comprehensive Review on Financial Explainable AI](https://mlsanity.com/paper/2309.11960/) (2023)
- [Implementing local-explainability in Gradient Boosting Trees: Feature Contribution](https://mlsanity.com/paper/2402.09197/) (2024)
- [Decorrelated feature importance from local sample weighting](https://mlsanity.com/paper/2508.06337/) (2025)
- [DELICATE: Diachronic Entity LInking using Classes And Temporal Evidence](https://mlsanity.com/paper/2511.10404/) (2025)
- [Woodelf++: A Fast and Unified Partial Dependence Plot Algorithm for Decision Tree Ensembles](https://mlsanity.com/paper/2605.14578/) (2026)

## Abstract (arXiv)

The recent increase in the deployment of machine learning models in critical domains such as healthcare, criminal justice, and finance has highlighted the need for trustworthy methods that can explain these models to stakeholders. Feature importance methods (e.g. gain and SHAP) are among the most popular explainability methods used to address this need. For any explainability technique to be trustworthy and meaningful, it has to provide an explanation that is accurate and stable. Although the stability of local feature importance methods (explaining individual predictions) has been studied before, there is yet a knowledge gap about the stability of global features importance methods (explanations for the whole model). Additionally, there is no study that evaluates and compares the accuracy of global feature importance methods with respect to feature ordering. In this paper, we evaluate the accuracy and stability of global feature importance methods through comprehensive experiments done on simulations as well as four real-world datasets. We focus on tree-based ensemble methods as they are used widely in industry and measure the accuracy and stability of explanations under two scenarios: 1) when inputs are perturbed 2) when models are perturbed. Our findings provide a comparison of these methods under a variety of settings and shed light on the limitations of global feature importance methods by indicating their lack of accuracy with and without noisy inputs, as well as their lack of stability with respect to: 1) increase in input dimension or noise in the data; 2) perturbations in models initialized by different random seeds or hyperparameter settings.