Explaining instance classifications with interactions of subsets of feature values

Authors:
E. Štrumbelj;I. Kononenko;M. Robnik Šikonja
Affiliations:
University of Ljubljana, Faculty of Computer and Information Science, Traška cesta 25, 1000 Ljubljana, Slovenia;University of Ljubljana, Faculty of Computer and Information Science, Traška cesta 25, 1000 Ljubljana, Slovenia;University of Ljubljana, Faculty of Computer and Information Science, Traška cesta 25, 1000 Ljubljana, Slovenia
Venue:
Data & Knowledge Engineering
Year:
2009

Citing 15
Cited 6

Enumerative combinatorics

Enumerative combinatorics
Extracting Refined Rules from Knowledge-Based Neural Networks

Machine Learning
Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
Random Forests

Machine Learning
An introduction to variable and feature selection

The Journal of Machine Learning Research
Toward Integrating Feature Selection Algorithms for Classification and Clustering

IEEE Transactions on Knowledge and Data Engineering
Nomograms for visualization of naive Bayesian classifier

PKDD '04 Proceedings of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases
Nomograms for visualizing support vector machines

Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
Evolutionary stratified training set selection for extracting classification rules with trade off precision-interpretability

Data & Knowledge Engineering
Strategies for improving the modeling and interpretability of Bayesian networks

Data & Knowledge Engineering
Explaining Classifications For Individual Instances

IEEE Transactions on Knowledge and Data Engineering
Machine Learning and Data Mining: Introduction to Principles and Algorithms

Machine Learning and Data Mining: Introduction to Principles and Algorithms
Visual explanation of evidence in additive classifiers

IAAI'06 Proceedings of the 18th conference on Innovative applications of artificial intelligence - Volume 2
A new outlook on Shannon's information measures

IEEE Transactions on Information Theory
Machine learning for medical diagnosis: history, state of the art and perspective

Artificial Intelligence in Medicine

An Efficient Explanation of Individual Classifications using Game Theory

The Journal of Machine Learning Research
Modeling the evolution of associated data

Data & Knowledge Engineering
Rough sets based association rules application for knowledge-based system design

ICCCI'10 Proceedings of the Second international conference on Computational collective intelligence: technologies and applications - Volume Part II
Efficiently explaining decisions of probabilistic RBF classification networks

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I
Quality of classification explanations with PRBF

Neurocomputing
Explaining data-driven document classifications

MIS Quarterly

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a novel method for explaining the decisions of an arbitrary classifier, independent of the type of classifier. The method works at the instance level, decomposing the model's prediction for an instance into the contributions of the attributes' values. We use several artificial data sets and several different types of models to show that the generated explanations reflect the decision-making properties of the explained model and approach the concepts behind the data set as the prediction quality of the model increases. The usefulness of the method is justified by a successful application on a real-world breast cancer recurrence prediction problem.