# Interpretable Random Forests via Rule Extraction

arXiv: https://arxiv.org/abs/2004.14841 · HTML: https://mlsanity.com/paper/2004.14841/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [Trading Complexity for Sparsity in Random Forest Explanations](https://mlsanity.com/paper/2108.05276/) (2021)
- [A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation](https://mlsanity.com/paper/2304.02858/) (2023)
- [Accurate Shapley Values for explaining tree-based models](https://mlsanity.com/paper/2106.03820/) (2021)
- [Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective](https://mlsanity.com/paper/2401.04374/) (2024)
- [Benchmarking XAI Explanations with Human-Aligned Evaluations](https://mlsanity.com/paper/2411.02470/) (2024)
- [Explainable Global Fairness Verification of Tree-Based Classifiers](https://mlsanity.com/paper/2209.13179/) (2022)
- [Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models](https://mlsanity.com/paper/2111.04658/) (2021)
- [Personalized and Reliable Decision Sets: Enhancing Interpretability in Clinical Decision Support Systems](https://mlsanity.com/paper/2107.07483/) (2021)
- [Orthogonal Gradient Boosting for Simpler Additive Rule Ensembles](https://mlsanity.com/paper/2402.15691/) (2024)
- [Explaining Predictions by Characteristic Rules](https://mlsanity.com/paper/2405.21003/) (2024)
- [Compact Rule-Based Classifier Learning via Gradient Descent](https://mlsanity.com/paper/2502.01375/) (2025)
- [Towards interpreting ML-based automated malware detection models: a survey](https://mlsanity.com/paper/2101.06232/) (2021)
- [Explaining Any ML Model? -- On Goals and Capabilities of XAI](https://mlsanity.com/paper/2206.13888/) (2022)
- [A Unified Approach to Extract Interpretable Rules from Tree Ensembles via Integer Programming](https://mlsanity.com/paper/2407.00843/) (2024)
- [Surrogate Interpretable Graph for Random Decision Forests](https://mlsanity.com/paper/2506.01988/) (2025)
- [Robust Model Compression Using Deep Hypotheses](https://mlsanity.com/paper/2103.07668/) (2021)
- [Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning](https://mlsanity.com/paper/2106.02824/) (2021)
- [Local and Regional Counterfactual Rules: Summarized and Robust Recourses](https://mlsanity.com/paper/2209.14568/) (2022)
- [Learning Locally Interpretable Rule Ensemble](https://mlsanity.com/paper/2306.11481/) (2023)
- [An Interpretable Rule Creation Method for Black-Box Models based on Surrogate Trees -- SRules](https://mlsanity.com/paper/2407.20070/) (2024)
- [S-SIRUS: an explainability algorithm for spatial regression Random Forest](https://mlsanity.com/paper/2408.05537/) (2024)
- [Minimax Rates and Spectral Distillation for Tree Ensembles](https://mlsanity.com/paper/2605.11841/) (2026)
- [Sparse Oblique Rule Boosting for Simpler Additive Rule Ensembles](https://mlsanity.com/paper/2609.06426/) (2026)

## Abstract (arXiv)

We introduce SIRUS (Stable and Interpretable RUle Set) for regression, a stable rule learning algorithm which takes the form of a short and simple list of rules. State-of-the-art learning algorithms are often referred to as "black boxes" because of the high number of operations involved in their prediction process. Despite their powerful predictivity, this lack of interpretability may be highly restrictive for applications with critical decisions at stake. On the other hand, algorithms with a simple structure-typically decision trees, rule algorithms, or sparse linear models-are well known for their instability. This undesirable feature makes the conclusions of the data analysis unreliable and turns out to be a strong operational limitation. This motivates the design of SIRUS, which combines a simple structure with a remarkable stable behavior when data is perturbed. The algorithm is based on random forests, the predictive accuracy of which is preserved. We demonstrate the efficiency of the method both empirically (through experiments) and theoretically (with the proof of its asymptotic stability). Our R/C++ software implementation sirus is available from CRAN.