The Community for Technology Leaders
Green Image
ABSTRACT
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.
INDEX TERMS
Machine learning, Data mining, Data and knowledge visualization, Visualization techniques and methodologies
CITATION
Igor Kononenko, Marko Robnik-Šikonja, "Explaining Classifications For Individual Instances", IEEE Transactions on Knowledge & Data Engineering, vol. 20, no. , pp. 589-600, May 2008, doi:10.1109/TKDE.2007.190734
107 ms
(Ver )