Fossil fuels being the primary source of energy for industrial and power sectors are being consumed at an alarming rate. There is a dire need to search for alternative fuels and optimize the performance parameters of internal combustion (IC) engines. Traditional methods of testing and optimizing the performances of IC engine are complex, time-consuming, and expensive. This has led the researchers to shift their focus to faster and computationally feasible techniques like soft computing (SC) and machine learning (ML) algorithms, which predict the optimum performance with a substantial accuracy. This study focuses on the implementation of artificial neural network (ANN) and ensembling methods (random forest regression and extreme gradient boosting algorithm) modeling of a compression ignition (CI) diesel engine run on waste cooking oil (WCO). A single-cylinder, four-stroke, variable compression ratio diesel engine's performance, combustion, and emission parameters have been predicted using ANN and ML approaches. These models have been developed to predict the brake power, brake thermal efficiency, brake-specific fuel consumption, ignition delay, combustion duration, carbon monoxide, carbon dioxide, and oxides of nitrogen. All the models have been trained by tuning and optimizing a different number of hyper-parameters and training algorithms (Levenberg–Marquardt (LM), scaled conjugate gradient, and Broyden–Fletcher–Goldfarb–Shanno). Further the most optimum parameters have been selected using hyper-parameter optimization. The mathematical models are assessed for their generalization capability by subjecting them to a set of new testing data.