1. Introduction and Motivations
Hybrid classification refers to the process of solving classification problems by leveraging both humans and ML [1]. Hybrid classification services have received little attention in the literature but, in our experience are by far the most common form of classification, especially in enterprise context. Almost invariably, when ML is adopted in the enterprise as well as in domains from medical to automotive, ML attempts an inference and a decision on whether to accept the inference or ask a human ensues, based on the prediction confidence.