In light of H2 emerging as a promising alternative to conventional fuels, our work focuses on finding suitable g-C3N4 based SAC’s for Hydrogen Evolution Reaction (HER). A three-tier screening based on formation energy, Gibbs free energy and band-gap is used to downselect suitable candidates. Also, a robust machine learning model is built based on the data generated from DFT as well as the features of gas-phase atoms present in the chemical composition. As a part of model development, the performance of Multivariate Linear Regression (MLR), Decision Tree Regression (DTR), and Random Forest Regression (RFR) are compared. In addition, feature importance analysis is employed to identify key descriptors for the HER.