Tag: explainable AI

Originally published at https://www.h2o.ai on April 21, 2021. It is impossible to deploy successful AI models without taking into account or analyzing the risk element involved. Model overfitting, perpetuating historical human bias, and data drift are some of the concerns that need to be taken care of before putting the models into production. At H2O.ai, Machine Learning … Continue reading Shapley summary plots: the latest addition to the H2O.ai’s Explainability arsenal