The Republic of Korea Air Force (ROKAF) spends hundreds of billions of Korean won annually on jet fuel, with price fluctuations posing a significant logistical and operational readiness challenge. Accurate price forecasting is crucial for optimizing fuel inventory management, yet existing research often focuses on macro-level economic indicators with limited practical application. This study investigates the potential of machine learning (ML) for enhancing jet fuel price forecasting accuracy. We propose ML models incorporating supply chain data, Google Trends data, and geopolitical factors alongside traditional economic variables for more realistic predictions. Our results demonstrate that a XGBoost model achieves the best performance, reducing Root Mean Squared Error (RMSE) by 67%. Adoption of this model by the ROKAF could significantly improve supply price management capabilities. Furthermore, the study's findings have broader applicability, potentially benefiting the inventory management of other commodities with significant price volatility and recurring purchases.