Model of Machine Learning for Prediction and Optimization of Oil and Gas Operating Costs in Indonesia

Bagaskoro, Adhanto
Nengkoda, Ardian
Sommeng, Andy Noorsaman

Formosa Journal of Science and Technology (FJST)
Vol. 3 No. 6 (2024): June 2024

This study leverages machine learning techniques to predict and optimize operational expenditures (OPEX) in Indonesia's oil and gas industry. By analyzing historical data from Work Plan and Budget (WP&B) reports from 2017, the research identifies key factors influencing OPEX, such as production location, oil characteristics, and development stages. The Random Forest model demonstrated the highest predictive accuracy with an R-squared value of 0.92 and Mean Squared Error (MSE) of 4.5. The findings highlight significant cost-saving opportunities, particularly in Kalimantan and Papua. These insights support strategic planning and decision-making, emphasizing the transformative potential of machine learning in enhancing operational efficiency and sustainability in the oil and gas sector.