Reference Class Forecasting and Machine Learning for Improved Offshore Oil and Gas Megaproject Planning: Methods and Application

Abstract

This article develops and describes rigorous oil and gas project forecasting methods. First, it builds a theoretical foundation by mapping megaproject performance literature to these projects. Second, it draws on heuristics and biases literature, using a questionnaire to demonstrate forecasting-related biases and principal-agent issues among industry project professionals. Third, it uses methodically collected project performance data to demonstrate that overrun distributions are non-normal and fat-tailed. Fourth, reference-class forecasting is demonstrated for cost and schedule uplifts. Finally, a predictive approach using machine learning (ML) considers project-specific factors to forecast the most likely cost and schedule overruns in a project.