Incorporating experts’ judgment into machine learning models

Machine learning (ML) models have been quite successful in predicting outcomes many applications. However, some cases, domain experts might a judgment about the expected outcome that conflict with prediction of ML models. One main reason for this is training data not be totally representative population. In paper, we present novel framework aims at leveraging experts' to mitigate conflict. The underlying idea behind our first determine, using generative adversarial network, degree representation an unlabeled point data. Then, based on such degree, correct \textcolor{black}{machine learning} model's by incorporating into it, where higher aforementioned representation, less weight put expert intuition add corrected output, and vice-versa. We perform multiple numerical experiments synthetic as well two real-world case studies (one from IT services industry other financial industry). All results show effectiveness framework; it yields much closeness minimal sacrifice accuracy, when compared baseline methods. also develop new evaluation metric combines accuracy judgment. Our statistically significant evaluated metric.