Evidence Counterfactuals for explaining predictive models on Big Data

Big Data generated by people -- such as, social media posts, mobile phone GPS locations, and browsing history -- provide enormous prediction value for AI systems. However, explaining how these models predict with the data remains challenging. This interesting explanation approach considers how a model would behave if it didn't have the original set of data to work with.

Check out the full article at KDNuggets.com website
Evidence Counterfactuals for explaining predictive models on Big Data