ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911588169023488 |
|---|---|
| author | Bewley, Tom Amoukou, Salim I. Albini, Emanuele Mishra, Saumitra Veloso, Manuela |
| author_facet | Bewley, Tom Amoukou, Salim I. Albini, Emanuele Mishra, Saumitra Veloso, Manuela |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11200 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values Bewley, Tom Amoukou, Salim I. Albini, Emanuele Mishra, Saumitra Veloso, Manuela Machine Learning Artificial Intelligence 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. |
| title | ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.11200 |