An Efficient Explanation of Individual Classifications using Game Theory 论文
2010Repository of the University of Ljubljana (University of Ljubljana)引用 385
Machine Learning and Data ClassificationImbalanced Data Classification TechniquesBayesian Modeling and Causal Inference
摘要
We present a general method for explaining individual predictions of classification models. The method is based on fundamental concepts from coalitional game theory and predictions are explained with contributions of individual feature values. We overcome the method's initial exponential time complexity with a sampling-based approximation. In the experimental part of the paper we use the developed method on models generated by several well-known machine learning algorithms on both synthetic and real-world data sets. The results demonstrate that the method is efficient and that the explanations are intuitive and useful.