Clustering-Based Analysis of Fuel Efficiency and Emissions in Automotive Data Using PCA and K-Means

Growing concerns regarding greenhouse gas emissions and fuel consumption have placed considerable demands on the automotive sector. To address these issues, this research applies unsupervised learning approaches namely Principal Component Analysis (PCA) and K-Means Clustering to categorize vehicles based on attributes associated with energy efficiency and environmental impact. Using a publicly available vehicle dataset, PCA was used to simplify the data by reducing dimensionality while preserving significant patterns. Subsequently, K-Means was employed to segment the data into three distinct clusters according to shared features like engine size, fuel usage, and CO₂ output. The resulting groupings effectively identified categories such as fuel-efficient, moderately consuming, and high-consumption vehicles. Visual representation in two-dimensional space further confirmed meaningful distinctions among the clusters, offering practical insights for both manufacturers and consumers.