# Fast Calculation of Feature Contributions in Boosting Trees

arXiv: https://arxiv.org/abs/2407.03515 · HTML: https://mlsanity.com/paper/2407.03515/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [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)
- [Interpretability of machine learning based prediction models in healthcare](https://mlsanity.com/paper/2002.08596/) (2020)
- [Efficient nonparametric statistical inference on population feature importance using Shapley values](https://mlsanity.com/paper/2006.09481/) (2020)
- [RKHS-SHAP: Shapley Values for Kernel Methods](https://mlsanity.com/paper/2110.09167/) (2021)
- [Fast TreeSHAP: Accelerating SHAP Value Computation for Trees](https://mlsanity.com/paper/2109.09847/) (2021)
- [SHAFF: Fast and consistent SHApley eFfect estimates via random Forests](https://mlsanity.com/paper/2105.11724/) (2021)
- [Linear TreeShap](https://mlsanity.com/paper/2209.08192/) (2022)

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

- [Amortized Linear-time Exact Shapley Value for Product-Kernel Methods](https://mlsanity.com/paper/2505.16516/) (2025)
- [TreeGrad-Ranker: Feature Ranking via O(L)-Time Gradients for Decision Trees](https://mlsanity.com/paper/2602.11623/) (2026)
- [qshap: Fast Shapley Decomposition of R2 for Gradient-Boosted Trees](https://mlsanity.com/paper/2608.24104/) (2026)

## Abstract (arXiv)

Recently, several fast algorithms have been proposed to decompose predicted value into Shapley values, enabling individualized feature contribution analysis in tree models. While such local decomposition offers valuable insights, it underscores the need for a global evaluation of feature contributions. Although coefficients of determination (R2) allow for comparative assessment of individual features, individualizing R2 is challenged by the underlying quadratic losses. To address this, we propose Q-SHAP, an efficient algorithm that reduces the computational complexity of calculating Shapley values for quadratic losses to polynomial time. Our simulations show that Q-SHAP not only improves computational efficiency but also enhances the accuracy of feature-specific R2 estimates.