Predictive Analysis of Cost Overruns and Additives in Integrated Energy Infrastructure Contracts: Integration of BIM, P Schedules, and Machine Learning - A Systematic Literature Review

Effective cost management in energy infrastructure projects represents one of the greatest contemporary challenges in the construction industry, with systematic cost overruns reaching averages of 40 % to 200 % depending on the project type . This article presents a systematic literature review on the predictive analysis of cost overruns and additives in integrated energy infrastructure contracts, focusing on the integration of Building Information Modeling (BIM), Primavera P schedules, and machine learning techniques. The systematic review methodology followed PRISMA guidelines, analyzing articles published between and in journals classified as A1 and A2 . The results reveal that the integration of these three technologies can reduce cost overruns by 20-40% and improve estimation accuracy by %. Significant gaps were identified in the literature, particularly in the specific application to energy infrastructure projects and in the complete integration of the three technologies. The study proposes an innovative conceptual framework that integrates BIM, P schedules, and machine learning algorithms for the predictive analysis of cost overruns in integrated contracts. The main contributions include: a systematic mapping of the state of the art, ( ) the identification of research gaps, the proposal of an integrated framework, and ( ) directions for future research. The findings indicate that the adoption of integrated approaches can significantly transform cost management in energy infrastructure projects, providing greater accuracy, transparency, and risk control.