# Predictive and Causal Implications of using Shapley Value for Model Interpretation

arXiv: https://arxiv.org/abs/2008.05052 · HTML: https://mlsanity.com/paper/2008.05052/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 16 of 16)

- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [SHAP-XRT: The Shapley Value Meets Conditional Independence Testing](https://mlsanity.com/paper/2207.07038/) (2022)
- [VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks](https://mlsanity.com/paper/2307.02040/) (2023)
- [Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models](https://mlsanity.com/paper/2203.16073/) (2022)
- [The Shapley Value of coalition of variables provides better explanations](https://mlsanity.com/paper/2103.13342/) (2021)
- [Causal-discovery-based root-cause analysis and its application in time-series prediction error diagnosis](https://mlsanity.com/paper/2411.06990/) (2024)
- [A Comprehensive Study of Shapley Value in Data Analytics](https://mlsanity.com/paper/2412.01460/) (2024)
- [REX: Causal discovery based on machine learning and explainability techniques](https://mlsanity.com/paper/2501.12706/) (2025)
- [Improving Fairness in Adaptive Social Exergames via Shapley Bandits](https://mlsanity.com/paper/2302.09298/) (2023)
- [Whole-Genome Phenotype Prediction with Machine Learning: Open Problems in Bacterial Genomics](https://mlsanity.com/paper/2502.07749/) (2025)
- [Why are there many equally good models? An Anatomy of the Rashomon Effect](https://mlsanity.com/paper/2601.06730/) (2026)
- [MinShap: A Shapley-Based Framework for Feature Redundancy](https://mlsanity.com/paper/2604.15107/) (2026)
- [Position-based Contributive Embeddings for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2108.05098/) (2021)
- [Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction](https://mlsanity.com/paper/2202.05139/) (2022)
- [Beyond Additivity: Sparse Isotonic Shapley Regression toward Nonlinear Explainability](https://mlsanity.com/paper/2512.03112/) (2025)

## Abstract (arXiv)

Shapley value is a concept from game theory. Recently, it has been used for explaining complex models produced by machine learning techniques. Although the mathematical definition of Shapley value is straight-forward, the implication of using it as a model interpretation tool is yet to be described. In the current paper, we analyzed Shapley value in the Bayesian network framework. We established the relationship between Shapley value and conditional independence, a key concept in both predictive and causal modeling. Our results indicate that, eliminating a variable with high Shapley value from a model do not necessarily impair predictive performance, whereas eliminating a variable with low Shapley value from a model could impair performance. Therefore, using Shapley value for feature selection do not result in the most parsimonious and predictively optimal model in the general case. More importantly, Shapley value of a variable do not reflect their causal relationship with the target of interest.