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.

Data analytics for project delivery: unlocking the potential of an emerging field

“…Even though some studies explored the adoption of reference classing forecasting (Batselier and Vanhoucke, 2016; Natarajan, 2022), the construct of “reference classes” is still a limitation of the use of machine learning not explored in either the grey or white literature (Whyte et al. , 2016).…”

“…Even though some studies explored the adoption of reference classing forecasting (Batselier and Vanhoucke, 2016;Natarajan, 2022), the construct of "reference classes" is still a limitation of the use of machine learning not explored in either the grey or white literature (Whyte et al, 2016). If the project is very novel, the machine learning prediction will not be effective as it will not match existing references classes.…”

An integrated DEMATEL and system dynamic model for project cost prediction

“…Cost issues that affect the owner cover the variation of the contract cost from the anticipated cost during the planning phase (cost deviation) and the change in the contract cost at the project's completion (change in contract cost and scope). Various types of research investigated cost deviation or contract cost change by identifying the most critical factors or developing forecast models for them [ [6] , [7] , [8] , [9] , [10] , [11] , [12] , [13] , [14] , [15] , [16] ].…”

Contractor Companies’ Small Projects Facing Mining 4.0 in Chile: How Risky Is the Implementation of Industry 4.0 for Them?

“…It should be noted that contractors in the mining industry are often responsible for specific tasks or projects, such as drilling, excavation, transportation, maintenance, service or construction projects and by using industry 4.0 technologies, they can improve these tasks and streamline their workflows. In this way, the use of machine learning applications as a predictive approach to forecast the most likely cost and schedule overruns in projects have been tested in the oil and gas industry (Natarajan, 2022). In addition, and considering that it is imperative to have real-time information for optimum decision-making in modern mining, Industry 4.0 technologies are the mechanisms for integrating business systems, manufacturing systems and processes (Sishi and Telukdarie, 2020).…”