# Derivative-based Shapley value for global sensitivity analysis and machine learning explainability

arXiv: https://arxiv.org/abs/2303.15183 · HTML: https://mlsanity.com/paper/2303.15183/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 5 of 5)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [Explaining black box decisions by Shapley cohort refinement](https://mlsanity.com/paper/1911.00467/) (2019)

## Built on by (most cited first, 3 of 3)

- [Data-Driven Modelling for Harmonic Current Emission in Low-Voltage Grid Using MCReSANet with Interpretability Analysis](https://mlsanity.com/paper/2311.15420/) (2023)
- [Beyond Additivity: Sparse Isotonic Shapley Regression toward Nonlinear Explainability](https://mlsanity.com/paper/2512.03112/) (2025)
- [Which Hyperparameters Matter? A Game-Theoretic Framework for Interpretable Hyperparameter Sensitivity Analysis](https://mlsanity.com/paper/2607.15884/) (2026)

## Abstract (arXiv)

We introduce a new Shapley value approach for global sensitivity analysis and machine learning explainability. The method is based on the first-order partial derivatives of the underlying function. The computational complexity of the method is linear in dimension (number of features), as opposed to the exponential complexity of other Shapley value approaches in the literature. Examples from global sensitivity analysis and machine learning are used to compare the method numerically with activity scores, SHAP, and KernelSHAP.