A lasso regression-based forecasting model for daily gasoline consumption: Türkiye Case

Abstract

Gasoline is one of the most sought-after resources in the world, where the need for energy is indispensable and continuously increasing for human life today. A shortage of gasoline may negatively affect the economies of countries. Therefore, analysis and estimates about gasoline consumption are critical. Better forecast performance on gasoline consumption can serve the policymakers, managers, researchers, and other gasoline sector stakeholders. This study focuses on forecasting daily gasoline consumption in Türkiye using a lasso regression-based methodology. The methodology involves three main stages: cleaning data, extracting/selecting features, and forecasting future consumption. Additionally, Ridge Regression is employed for performance comparison. Results from the proposed methodology inform strategies for gasoline consumption, enabling more accurate planning and trade activities. The study emphasizes the importance of daily forecasts in deciding import quantities, facilitating timely planning, and establishing a well-organized gasoline supply chain system. Application of this methodology in Türkiye can pave the way for globally coordinated steps in gasoline consumption, establishing efficient gasoline supply chain systems. The findings provide insights for establishing a smooth and secure gasoline collection/distribution infrastructure, offering effective solutions to both public and private sectors. The proposed forecasting methodology serves as a reference for ensuring uninterrupted gasoline supply and maximizing engagement between customers and suppliers. Applied and validated for Türkiye, this methodology can guide global efforts, fostering planned approaches to gasoline consumption and enhancing supply chain systems.