Towards a Model Independent Method for Explaining Classification for Individual Instances

Authors:
Erik Štrumbelj;Igor Kononenko
Affiliations:
Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia 1000;Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia 1000
Venue:
DaWaK '08 Proceedings of the 10th international conference on Data Warehousing and Knowledge Discovery
Year:
2008

Citing 5
Cited 1

Random Forests

Machine Learning
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
Explaining Classifications For Individual Instances

IEEE Transactions on Knowledge and Data Engineering
Visual explanation of evidence in additive classifiers

IAAI'06 Proceedings of the 18th conference on Innovative applications of artificial intelligence - Volume 2

How to Explain Individual Classification Decisions

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, a method for explaining the model's decision for an instance was introduced by Robnik-Šikonja and Kononenko. It is a rare example of a model-independent explanation method. In this paper we make a step towards formalization of the model-independent explanation methods by defining the criteria and a testing environment for such methods. We extensively test the aforementioned method and its variations. The results confirm some of the qualities of the original method as well as expose several of its shortcomings. We propose a new method, based on attribute interactions, that overcomes the shortcomings of the original method and serves as a theoretical framework for further work.