Robust and eXplainable artificial intelligence
Paolo Giudici, Emanuela Raffinetti, Marco Riani · Research Square · 2023
Abstract Artificial Intelligence relies on the application of machine learning models which, while reaching high predictive accuracy, lack explainability and robustness. This is a problem in regulated industries, as authorities aimed at monitoring the risks arising from the application of AI methods may not validate them. No measurement methodologies are yet available to jointly assess accuracy, explainability and robustness of machine learning models. We propose a methodology which fills the gap, extending the forward search approach, employed in robust statistical learning, to machine learning models. Doing so, we will be able to evaluate, by means of interpretable statistical tests, whether a specific AI application is accurate, explainable and robust, by means of a unifying methodology. We apply our proposal to the context of bitcoin price prediction, comparing a linear regression model against a non linear neural network model.