An Efficient Explanation of Individual Classifications using Game Theory

  title={An Efficient Explanation of Individual Classifications using Game Theory},
  author={E. {\vS}trumbelj and I. Kononenko},
  journal={J. Mach. Learn. Res.},
  • E. Štrumbelj, I. Kononenko
  • Published 2010
  • Computer Science, Mathematics
  • J. Mach. Learn. Res.
  • We present a general method for explaining individual predictions of classification models. The method is based on fundamental concepts from coalitional game theory and predictions are explained with contributions of individual feature values. We overcome the method's initial exponential time complexity with a sampling-based approximation. In the experimental part of the paper we use the developed method on models generated by several well-known machine learning algorithms on both synthetic and… CONTINUE READING
    217 Citations
    The Explanation Game: Explaining Machine Learning Models with Cooperative Game Theory
    • 11
    • Highly Influenced
    • PDF
    Explaining prediction models and individual predictions with feature contributions
    • 237
    A Game Theoretic Approach to Class-wise Selective Rationalization
    • 11
    • PDF
    Explainable Artificial Intelligence: How Subsets of the Training Data Affect a Prediction
    • Highly Influenced
    • PDF
    Explainable Voting
    • PDF
    Quality of classification explanations with PRBF
    • 8
    • PDF
    shapr: An R-package for explaining machine learning models with dependence-aware Shapley values
    • 2
    • PDF
    Explaining individual predictions when features are dependent: More accurate approximations to Shapley values
    • 46
    • PDF


    Feature Selection via Coalitional Game Theory
    • 75
    • PDF
    Explaining Classifications For Individual Instances
    • 180
    • PDF
    Polynomial calculation of the Shapley value based on sampling
    • 210
    Explaining instance classifications with interactions of subsets of feature values
    • 61
    • PDF
    Visual Explanation of Evidence with Additive Classifiers
    • 104
    • PDF
    Contact personalization using a score understanding method
    • 33
    • PDF
    Wrappers for Feature Subset Selection
    • 7,690
    • PDF
    Random Forests
    • L. Breiman
    • Mathematics, Computer Science
    • Machine Learning
    • 2004
    • 50,919
    • PDF
    Visualizing the Simple Bayesian Classi er
    • 41
    • PDF