Deterministic and probabilistic risk management methods in construction projects: A systematic literature review and comparative analysis
Loading...
Supplementary material
Other Title
Authors
Khodabakshian, A.
Puolitaival, Taija
Kestle, Linda
Puolitaival, Taija
Kestle, Linda
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2022
Supervisors
Type
Conference Contribution - Paper in Published Proceedings
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
construction industry
project management
risk management framework
machine learning
artificial intelligence (AI)
project management
risk management framework
machine learning
artificial intelligence (AI)
ANZSRC Field of Research Code (2020)
Citation
Khodabakshian, A., Puolitaival, T., & Kestle, L. (2022). Deterministic and probabilistic risk management methods in construction projects: A systematic literature review and comparative analysis. In S. Perera and M. Hardie (Eds.). Global challenges in a disrupted world: Smart, sustainable and resillent approaches in the built environment, AUBEA Conference 2022. (pp. 317-327). Western Sydney University on behalf of AUBEA. doi:10.26183/a6pq-mg06
Abstract
Risks and uncertainties are inevitable in construction projects, and can drastically change the expected outcome, and negatively impact the project's success. However, Risk Management (RM) is still conducted in a manual, ineffective, and experience-based fashion in practice, hindering automation and knowledge transfer to upcoming projects. The Construction industry is recently benefitting from Industry 4.0 revolution and the advancements of Data Science branches such as Artificial Intelligence (AI). This shifts the construction management processes towards digitalization and optimization. Datadriven methods, such as AI and Machine Learning algorithms, Bayesian Inference, and Fuzzy Logic, seem to be a decent solution to RM domain shortcomings and automating and optimizing the RM processes, which are being widely explored recently. These methods are divided into deterministic and probabilistic models, the first of which proposes a fixed predicted value, and the latter, embraces the notion of uncertainty, causal dependencies, and inferences between variables affecting projects' risk when proposing a predicted value. This research uses a systematic literature review to investigate and then comparatively analyse the main deterministic and probabilistic methods applied to Risk Management in the construction industry in respect of each method's specific scope, primary applications, advantages, disadvantages, method limitations, and proven accuracy. The findings will establish the recommendations for optimum AI-based methods and frameworks for different management levels- Strategic, Operational Project Management, and for large or small datasets.
Publisher
Western Sydney University on behalf of AUBEA
Permanent link
Link to ePress publication
DOI
doi:10.26183/a6pq-mg06
Copyright holder
© Copyright in individual articles contained in the Proceedings of the AUBEA 2022 Conference is vested in each of the authors.
Copyright notice
All rights reserved