# ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values

arXiv: https://arxiv.org/abs/2604.11200 · HTML: https://mlsanity.com/paper/2604.11200/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 13 Apr 2026.

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

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models](https://mlsanity.com/paper/2107.00758/) (2021)
- [Diagnosing Model Performance Under Distribution Shift](https://mlsanity.com/paper/2303.02011/) (2023)
- [Towards Explaining Distribution Shifts](https://mlsanity.com/paper/2210.10275/) (2022)
- [Monitoring and explainability of models in production](https://mlsanity.com/paper/2007.06299/) (2020)
- ["Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts](https://mlsanity.com/paper/2210.10769/) (2022)
- [FairCanary: Rapid Continuous Explainable Fairness](https://mlsanity.com/paper/2106.07057/) (2021)
- [Human-interpretable model explainability on high-dimensional data](https://mlsanity.com/paper/2010.07384/) (2020)
- [Explanation Shift: Detecting distribution shifts on tabular data via the explanation space](https://mlsanity.com/paper/2210.12369/) (2022)
- [One or Two Things We know about Concept Drift -- A Survey on Monitoring Evolving Environments](https://mlsanity.com/paper/2310.15826/) (2023)
- [Machine Learning Model Drift Detection Via Weak Data Slices](https://mlsanity.com/paper/2108.05319/) (2021)
- [Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions](https://mlsanity.com/paper/2406.02625/) (2024)
- [Unified Shapley Framework to Explain Prediction Drift](https://mlsanity.com/paper/2102.07862/) (2021)
- [A hierarchical decomposition for explaining ML performance discrepancies](https://mlsanity.com/paper/2402.14254/) (2024)
- ["What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts](https://mlsanity.com/paper/2403.05652/) (2024)
- [The Lifecycle of a Statistical Model: Model Failure Detection, Identification, and Refitting](https://mlsanity.com/paper/2202.04166/) (2022)

## Abstract (arXiv)

Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's loan approval rate), so understanding their causes can be crucial. We propose ours: a Shapley value method for attributing prediction shifts to changes in the conditional probabilities of interpretable subgroups of data, where these subgroups are defined by the structure of decision trees. We initially apply this method to single decision trees, providing exact explanations based on conditional probability changes at split nodes. Next, we extend it to tree ensembles by selecting the most explanatory tree and accounting for residual effects. Finally, we propose a model-agnostic variant using surrogate trees grown with a novel objective function, allowing application to models like neural networks. While exact computation can be intensive, approximation techniques enable practical application. We show that ours provides simple, faithful, and near-complete explanations of prediction shifts across model classes, aiding model monitoring in dynamic environments.