A Regression-Based Model for Estimating Motorcycle Fuel Consumption

This study aimed to develop a regression-based model for estimating motorcycle fuel consumption using real-world commuting data, addressing the gap between manufacturer-reported fuel efficiency and actual riding conditions. Data were obtained from the Spritmonitor database and analyzed using quantitative statistical methods, including descriptive statistics, correlation analysis, and multiple linear regression, with fuel consumption expressed in liters per 100 kilometers as the dependent variable and travel distance, speed category, and fuel type as independent variables. Results showed that motorcycle fuel consumption is significantly influenced by operational factors, particularly travel distance and speed, where longer continuous trips were associated with improved fuel efficiency and higher speeds resulted in increased fuel consumption. Fuel type, however, did not exhibit a statistically significant effect within the observed commuting conditions. The regression model demonstrated high predictive accuracy, with low error values and an overall accuracy of 98.48%, indicating close agreement between actual and predicted fuel consumption values. These findings suggest that real-world operational conditions play a more critical role in determining motorcycle fuel consumption than fuel characteristics alone. The study concludes that regression analysis is an effective and practical approach for estimating motorcycle fuel consumption and provides a reliable, data-driven model that can be used by riders, engineers, and transportation planners to better understand and manage fuel efficiency under everyday commuting scenarios.