ICIE 1.0: A Novel Tool for Interactive Contextual Interaction Explanations
With the rise of new laws around privacy and awareness, explanation of automated decision making becomes increasingly important. Nowadays, machine learning models are used to aid experts in domains such as banking and insurance to find suspicious transactions, approve loans and credit card applications. Companies using such systems have to be able to provide the rationale behind their decisions; blindly relying on the trained model is not sufficient. There are currently a number of methods that provide insights in models and their decisions, but often they are either good at showing global or local behavior. Global behavior is often too complex to visualize or comprehend, so approximations are shown, and visualizing local behavior is often misleading as it is difficult to define what local exactly means (i.e. our methods don’t “know” how easily a feature-value can be changed; which ones are flexible, and which ones are static). We introduce the ICIE framework (Interactive Contextual Interaction Explanations) which enables users to view explanations of individual instances under different contexts. We will see that various contexts for the same case lead to different explanations, revealing different feature interactions.
KeywordsExplanations Feature contributions Feature interactions Model transparency Awareness Trust Responsible analytics
- 3.Dheeru, D., Karra Taniskidou, E.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
- 6.Lundberg, S.M., Erion, G.G., Lee, S.-I.: Consistent individualized feature attribution for tree ensembles, arXiv preprint arXiv:1802.03888 (2018)
- 7.Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Conference Proceedings on Advances in Neural Information Processing Systems, pp. 4768–4777 (2017)Google Scholar
- 8.Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you? Explaining the predictions of any classifier. In: Proceedings of KDD, pp. 1135–1144 (2016)Google Scholar