Fuel efficiency is a crucial factor in the automotive industry because it directly influences fuel cost, vehicle performance, and environmental impact. With the increasing demand for energy-efficient transportation and growing concerns about carbon emissions, predicting fuel efficiency accurately has become important. This paper proposes a Smart Fuel Efficiency Estimation and Performance Optimization system that uses machine learning techniques to estimate vehicle fuel consumption based on various engine and operational parameters. The system analyzes parameters such as engine size, number of cylinders, transmission type, fuel type, vehicle class, and CO₂ rating to estimate fuel efficiency. A dataset representing different vehicle configurations is processed using data preprocessing techniques including encoding and feature scaling. A Linear Regression machine learning model is trained to learn the relationship between vehicle parameters and fuel consumption. The trained model is integrated with a web-based interface developed using Streamlit that allows users to input vehicle specifications and obtain instant fuel efficiency predictions. The model performance is evaluated using Mean Squared Error (MSE) and R-squared (R²) metrics. Experimental results show that the proposed system provides reliable predictions and helps users understand how different vehicle parameters influence fuel efficiency. The system demonstrates the effectiveness of machine learning in analyzing vehicle performance and supporting efficient fuel consumption management.