Machine learning in prediction of fuel efficiency in the automotive industry

This study explores how machine learning algorithms can help to increase fuel efficiency. The implemented model is trained based on a dataset that consists of many features and attributes affecting a vehicle’s fuel efficiency such as MPG, Number of cylinders, Horsepower, Vehicle weight, and many more. For training the model, many machine learning models that fit the dataset variables were studied and implemented. It was found that the Random Forest Regression technique performed better than other algorithms in predicting fuel economy after extensive testing and analysis. It was the most appropriate algorithm for my research goal because of its capacity to manage intricate interactions between the input variables and accurately anticipate fuel usage. Random Forest Regression was demonstrated to be a potent approach to improving fuel economy prediction accuracy by utilizing the ensemble of decision trees and feature unpredictability.This study's conclusion emphasizes the enormous potential of machine learning for enhancing fuel efficiency in the automotive sector. It was determined that Random Forest Regression is the best technique for forecasting fuel efficiency after investigation. It paved the path for improvements in resource optimization and environmental sustainability by taking into account several important criteria and investigating alternative algorithms. The objective is to encourage industry leaders to use machine learning as a catalyst for change, advancing the automobile industry toward a greener and more effective future.