Among various fuel cells (FCs), Polymer exchange membrane FC (PEMFC) plays a vital role in the transportation era because they operate at moderate temperatures, have quick start-up, are highly efficient, have scalable size, have high energy density etc. With a high degree of accuracy, machine learning algorithms (MLAs) can be applied to solve nonlinear problems in FCs, including performance prediction, service life prediction, and fault diagnostics. In addition to carrying out the optimization of operational parameters and design, MLAs when paired with optimization techniques may effectively and accurately accomplish a variety of optimization goals. The main objective of this study is to explain the significance of MLAs in PEMFC research and describe the prediction of operating parameters at which the PEMFC performance is maximized. This paper is structured to study the influence of different process parameters such as system temperature, fuel supply pressure, air supply pressure, fuel flow rate and air flow rate on the output voltage of the FC. It is clearly observed that the system temperature has significant percentage contribution as 96.92% on FC current and 86.22% on FC voltage compared to other parameters. Different MLAs are modelled to explore the PEMFC performance and results proved that gradient boosting regression provides better predictions compared to other algorithms such as decision tree regressor, support vector machine regressor, and random forest regression.