Using machine learning algorithms for the impact of driver behaviors on fuel efficiency and the determination of propensity towards electric vehicles

This study aims to examine the impact of driver behaviors on fuel consumption and energy efficiency, as well as to analyze the factors influencing the adoption of electric vehicles. The study utilized data collected through an online survey involving 304 participants, which covered demographic characteristics, driving habits, and attitudes toward electric vehicles. The collected data were analyzed using machine learning techniques to evaluate how driver behaviors affect fuel efficiency and interest in electric vehicles. The analyses revealed that interest in electric vehicles is influenced by factors such as knowledge level, cost perception, and infrastructure accessibility. Variations in interest levels were observed across age groups, with the 30-39 age group demonstrating the highest interest. It was noted that increasing knowledge levels and charging accessibility consistently elevated interest levels. Additionally, the relationships between driving experience, aggressive driving behaviors, and fuel consumption awareness were assessed, demonstrating that more conscious driving techniques can enhance fuel efficiency. The study employed machine learning models such as Random Forest, XGBoost, Logistic Regression, and SVM, and addressed class imbalances using the SMOTE technique. Among these models, the XGBoost model achieved the highest accuracy rate of 100%. The findings provide critical insights for promoting sustainable driving habits and developing strategies to accelerate the adoption of electric vehicles.