Explaining Classifications For Individual Instances

TLDR

The study proposes a method to explain predictions for individual instances. The method decomposes model predictions into individual attribute contributions and is applicable to any probability‑output classification model, including black‑box and ensemble methods. Experiments show that the explanations accurately reflect the models and a visualization tool demonstrates their usefulness and allows comparison across prediction methods.

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.