Explaining Classifications For Individual Instances

9 years 10 months ago
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 decomposition of a model's predictions on individual contributions of each attribute. Our method works for 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 which shows the utility of our approach and enables the comparison of different prediction methods.
Marko Robnik-Sikonja, Igor Kononenko
Added 15 Dec 2010
Updated 15 Dec 2010
Type Journal
Year 2008
Where TKDE
Authors Marko Robnik-Sikonja, Igor Kononenko
Comments (0)