Machine learning is gaining rapid popularity as a tool of choice for applications in almost every field. In the oil and gas industry, machine learning is used as a tool for solving problems which could not be solved by traditional methods or for providing a cost-effective and faster data driven solution. Engineering expertise and knowledge of fundamentals remain relevant and necessary to draw meaningful conclusions from the data-based models. Two case studies are presented in different applications that will illustrate the importance of using engineering domain knowledge for feature extraction and feature manipulation in creating insightful machine learning models. The first case study involves condition-based monitoring (CBM) of pumps. A variety of pumps are employed in all aspects of the oilfield life cycle, such as drilling, completion (including hydraulic fracturing), production, and intervention. There is no well-established method to monitor the pump fault states as they are operating based on sensor feedback. As a result, maintenance is performed either prematurely or reactively, both of which result in wasteful downtime and unnecessary expense. A machine learning based neural network model is used for identifying different fault states in a triplex pump from measured pressure sensor data. In the second case study, failures of mooring lines of an offshore floating production unit are predicted from the vessel position data. Identifying a damaged mooring line can be critical for the structural health of the floating production system. In offshore floating platforms, mooring line tension is highly correlated to a vessel’s motions. The vessel position data is created from running coupled analysis models. A K-Nearest-Neighbor (KNN) classifier model is trained to predict mooring line failures. In all the case studies, the importance of combining a deep understanding of the physics of the problem with machine learning tools is emphasized.