# First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution

arXiv: https://arxiv.org/abs/2603.22346 · HTML: https://mlsanity.com/paper/2603.22346/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 52 references that are in the map.
- First posted on arXiv 22 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [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 Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [Impossibility Theorems for Feature Attribution](https://mlsanity.com/paper/2212.11870/) (2022)
- [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://mlsanity.com/paper/2007.04131/) (2020)
- [Provably Better Explanations with Optimized Aggregation of Feature Attributions](https://mlsanity.com/paper/2406.05090/) (2024)
- [Explanation Multiplicity in SHAP: Characterization and Assessment](https://mlsanity.com/paper/2601.12654/) (2026)

## Abstract (arXiv)

We identify first-mover bias -- path-dependent concentration of SHAP feature importance from sequential residual fitting in gradient boosting -- as a mechanistic contributor to attribution instability under multicollinearity. Scaling up a single model amplifies this effect: a Large Single Model matching our method's total tree count produces the poorest attribution reproducibility of any approach tested. We show that model independence largely neutralizes first-mover bias. Both DASH (Diversified Aggregation of SHAP) and simple seed-averaging (Stochastic Retrain) restore stability by breaking the sequential dependency chain. At rho=0.9, both achieve stability ~0.977, while Single Best degrades to 0.958 and LSM to 0.938. On Breast Cancer, DASH improves stability from 0.376 to 0.925 (+0.549), outperforming Stochastic Retrain by +0.063. Under nonlinear DGPs, the advantage emerges at rho>=0.7. DASH provides two diagnostic tools -- the Feature Stability Index and Importance-Stability Plot -- that detect first-mover bias without ground truth. A crossed ANOVA with formal F-statistics confirms the mechanism: DASH shifts variance from model-dominated (40.6%) to data-dominated (73.6%). Software at https://github.com/DrakeCaraker/dash-shap