ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values

• URL: http://arxiv.org/abs/2604.11200v1
• Date: Mon, 13 Apr 2026 08:56:51 GMT
• Title: ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
• Abstract summary: Changes in input distribution can induce shifts in the average predictions of machine learning models.<n>We propose ours: a Shapley value method for attributing prediction shifts to changes in the conditional probabilities of interpretable subgroups of data.<n>We show that ours provides simple, faithful, and near-complete explanations of prediction shifts across model classes.
• Score: 21.035730606359174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Simultaneous Latent Budget Trees for Stratified Classification [0.11744028458220425]
  This paper introduces Simultaneous Latent Budget Trees, a probabilistic machine learning framework for classification trees.<n>A model-based split rule is proposed in which child nodes are interpreted as latent components of a simultaneous mixture model.<n>The proposed methodology is applied to investigate gender-related differences in disease progression of Amyotrophic Lateral Sclerosis.
  arXiv  Detail & Related papers  (2026-06-11T12:48:30Z)
• Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors [61.92704516732144]
  We show that the most robust features for correctness prediction are those that play a distinctive causal role in the model's behavior.<n>We propose two methods that leverage causal mechanisms to predict the correctness of model outputs.
  arXiv  Detail & Related papers  (2025-05-17T00:31:39Z)
• Explainable Clustering Beyond Worst-Case Guarantees [5.65604054654671]
  We study the explainable clustering problem first posed by Moshkovitz, Dasgupta, Rashtchian, and Frost (ICML 2020)<n>The goal of explainable clustering is to fit an axis-aligned decision tree with $K$ leaves and minimal clustering cost (where every leaf is a cluster)
  arXiv  Detail & Related papers  (2024-11-03T14:00:20Z)
• Building Trees for Probabilistic Prediction via Scoring Rules [0.0]
  We study modifying a tree to produce nonparametric predictive distributions. We find the standard method for building trees may not result in good predictive distributions. We propose changing the splitting criteria for trees to one based on proper scoring rules.
  arXiv  Detail & Related papers  (2024-02-16T20:04:13Z)
• Grouping Shapley Value Feature Importances of Random Forests for explainable Yield Prediction [0.8543936047647136]
  We explain the concept of Shapley values directly computed for groups of features and introduce an algorithm to compute them efficiently on tree structures. We provide a blueprint for designing swarm plots that combine many local explanations for global understanding.
  arXiv  Detail & Related papers  (2023-04-14T13:03:33Z)
• Unboxing Tree Ensembles for interpretability: a hierarchical visualization tool and a multivariate optimal re-built tree [0.34530027457862006]
  We develop an interpretable representation of a tree-ensemble model that can provide valuable insights into its behavior. The proposed model is effective in yielding a shallow interpretable tree approxing the tree-ensemble decision function.
  arXiv  Detail & Related papers  (2023-02-15T10:43:31Z)
• On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
  Differentiable causal discovery has proposed to factorize the data generating process into a set of modules. We study the generalization and adaption performance of such modular neural causal models. Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
  arXiv  Detail & Related papers  (2022-06-09T17:12:32Z)
• Distributional Gradient Boosting Machines [77.34726150561087]
  Our framework is based on XGBoost and LightGBM. We show that our framework achieves state-of-the-art forecast accuracy.
  arXiv  Detail & Related papers  (2022-04-02T06:32:19Z)
• Explaining random forest prediction through diverse rulesets [0.0]
  Local Tree eXtractor (LTreeX) is able to explain the forest prediction for a given test instance with a few diverse rules. We show that our proposed approach substantially outperforms other explainable methods in terms of predictive performance.
  arXiv  Detail & Related papers  (2022-03-29T12:54:57Z)
• Instance-Based Neural Dependency Parsing [56.63500180843504]
  We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set.
  arXiv  Detail & Related papers  (2021-09-28T05:30:52Z)
• Deducing neighborhoods of classes from a fitted model [68.8204255655161]
  In this article a new kind of interpretable machine learning method is presented. It can help to understand the partitioning of the feature space into predicted classes in a classification model using quantile shifts. Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed.
  arXiv  Detail & Related papers  (2020-09-11T16:35:53Z)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.