Explaining Classifications For Individual Instances

We present a method for explaining predictions for individual instances. The presented approach is general and can be used with all classification models that output probabilities. It is based on the decomposition of a model's predictions on individual contributions of each attribute. Our method works for the so-called black box models such as support vector machines, neural networks, and nearest neighbor algorithms, as well as for ensemble methods such as boosting and random forests. We demonstrate that the generated explanations closely follow the learned models and present a visualization technique that shows the utility of our approach and enables the comparison of different prediction methods.

[1]  Claude E. Shannon,et al.  A Mathematical Theory of Communications , 1948 .

[2]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[3]  L. J. Savage,et al.  Probability and the weighing of evidence , 1951 .

[4]  Elizabeth C. Hirschman,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[5]  A. Tversky,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[6]  J. Lubsen,et al.  A Practical Device for the Application of a Diagnostic or Prognostic Function , 1978, Methods of Information in Medicine.

[7]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[8]  Igor Kononenko,et al.  Inductive and Bayesian learning in medical diagnosis , 1993, Appl. Artif. Intell..

[9]  T. Liao.  Interpreting Probability Models: Logit, Probit, and Other Generalized Linear Models , 1994 .

[10]  Sebastian Thrun,et al.  Extracting Rules from Artifical Neural Networks with Distributed Representations , 1994, NIPS.

[11]  Jude W. Shavlik,et al.  Using Sampling and Queries to Extract Rules from Trained Neural Networks , 1994, ICML.

[12]  Jude W. Shavlik,et al.  in Advances in Neural Information Processing , 1996 .

[13]  Huan Liu,et al.  Understanding Neural Networks via Rule Extraction , 1995, IJCAI.

[14]  Joachim Diederich,et al.  Survey and critique of techniques for extracting rules from trained artificial neural networks , 1995, Knowl. Based Syst..

[15]  Visualizing the Simple Bayesian Classi er , 1997 .

[16]  Russell G. Almond,et al.  Graphical Explanation in Belief Networks , 1997 .

[17]  J. Robins,et al.  Marginal Structural Models and Causal Inference in Epidemiology , 2000, Epidemiology.

[18]  Krysia Broda,et al.  Symbolic knowledge extraction from trained neural networks: A sound approach , 2001, Artif. Intell..

[19]  Ronald J. Patton,et al.  Interpretation of Trained Neural Networks by Rule Extraction , 2001, Fuzzy Days.

[20]  Kary Främling.  Explaining Results of Neural Networks by Contextual Importance and Utility , 2003 .

[21]  Vasant Honavar,et al.  Towards simple, easy-to-understand, yet accurate classifiers , 2003, Third IEEE International Conference on Data Mining.

[22]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[23]  Jude W. Shavlik,et al.  Extracting refined rules from knowledge-based neural networks , 2004, Machine Learning.

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  François Poulet,et al.  SVM and graphical algorithms: a cooperative approach , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[26]  Martin Mozina,et al.  Nomograms for Visualization of Naive Bayesian Classifier , 2004, PKDD.

[27]  Ivan Bratko,et al.  Nomograms for visualizing support vector machines , 2005, KDD '05.

[28]  Henrik Jacobsson,et al.  Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review , 2005, Neural Computation.

[29]  Rich Caruana,et al.  Predicting good probabilities with supervised learning , 2005, ICML.

[30]  Duane Szafron,et al.  Visual Explanation of Evidence with Additive Classifiers , 2006, AAAI.

[31]  Lutz Hamel,et al.  Visualization of Support Vector Machines with Unsupervised Learning , 2006, 2006 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology.

[32]  Aristidis Likas,et al.  An Efficient Method for Explaining the Decisions of the Probabilistic RBF Classification Network , 2007 .