# SHAFF: Fast and consistent SHApley eFfect estimates via random Forests

arXiv: https://arxiv.org/abs/2105.11724 · HTML: https://mlsanity.com/paper/2105.11724/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 17 of 17)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R](https://mlsanity.com/paper/1508.04409/) (2015)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [Consistency of random forests](https://mlsanity.com/paper/1405.2881/) (2014)
- [Efficient nonparametric statistical inference on population feature importance using Shapley values](https://mlsanity.com/paper/2006.09481/) (2020)
- [Understanding Random Forests: From Theory to Practice](https://mlsanity.com/paper/1407.7502/) (2014)
- [Shapley Flow: A Graph-based Approach to Interpreting Model Predictions](https://mlsanity.com/paper/2010.14592/) (2020)
- [Iterative Random Forests to detect predictive and stable high-order interactions](https://mlsanity.com/paper/1706.08457/) (2017)
- [Understanding Global Feature Contributions With Additive Importance Measures](https://mlsanity.com/paper/2004.00668/) (2020)
- [MDA for random forests: inconsistency, and a practical solution via the Sobol-MDA](https://mlsanity.com/paper/2102.13347/) (2021)

## Built on by (most cited first, 22 of 22)

- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [WeightedSHAP: analyzing and improving Shapley based feature attributions](https://mlsanity.com/paper/2209.13429/) (2022)
- [Variance reduced Shapley value estimation for trustworthy data valuation](https://mlsanity.com/paper/2210.16835/) (2022)
- [A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them](https://mlsanity.com/paper/2305.09536/) (2023)
- [Decorrelated Variable Importance](https://mlsanity.com/paper/2111.10853/) (2021)
- [Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees](https://mlsanity.com/paper/2204.09938/) (2022)
- [Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration](https://mlsanity.com/paper/2510.16742/) (2025)
- [Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models](https://mlsanity.com/paper/2111.04658/) (2021)
- [Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models](https://mlsanity.com/paper/2209.11539/) (2022)
- [Efficient SAGE Estimation via Causal Structure Learning](https://mlsanity.com/paper/2304.03113/) (2023)
- [Attention-like feature explanation for tabular data](https://mlsanity.com/paper/2108.04855/) (2021)
- [Fast Calculation of Feature Contributions in Boosting Trees](https://mlsanity.com/paper/2407.03515/) (2024)
- [Shapley Curves: A Smoothing Perspective](https://mlsanity.com/paper/2211.13289/) (2022)
- [Interpretable Ensembles of Hyper-Rectangles as Base Models](https://mlsanity.com/paper/2303.08625/) (2023)
- [MMD-based Variable Importance for Distributional Random Forest](https://mlsanity.com/paper/2310.12115/) (2023)
- [Regional Explanations: Bridging Local and Global Variable Importance](https://mlsanity.com/paper/2604.11223/) (2026)
- [Local and Regional Counterfactual Rules: Summarized and Robust Recourses](https://mlsanity.com/paper/2209.14568/) (2022)
- [Dual feature-based and example-based explanation methods](https://mlsanity.com/paper/2401.16294/) (2024)
- [Provable Recovery of Locally Important Signed Features and Interactions from Random Forest](https://mlsanity.com/paper/2512.11081/) (2025)
- [Unity Forests: Improving Interaction Modelling and Interpretability in Random Forests](https://mlsanity.com/paper/2601.07003/) (2026)
- [qshap: Fast Shapley Decomposition of R2 for Gradient-Boosted Trees](https://mlsanity.com/paper/2608.24104/) (2026)

## Abstract (arXiv)

Interpretability of learning algorithms is crucial for applications involving critical decisions, and variable importance is one of the main interpretation tools. Shapley effects are now widely used to interpret both tree ensembles and neural networks, as they can efficiently handle dependence and interactions in the data, as opposed to most other variable importance measures. However, estimating Shapley effects is a challenging task, because of the computational complexity and the conditional expectation estimates. Accordingly, existing Shapley algorithms have flaws: a costly running time, or a bias when input variables are dependent. Therefore, we introduce SHAFF, SHApley eFfects via random Forests, a fast and accurate Shapley effect estimate, even when input variables are dependent. We show SHAFF efficiency through both a theoretical analysis of its consistency, and the practical performance improvements over competitors with extensive experiments. An implementation of SHAFF in C++ and R is available online.