EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence-Driven Project Risk Prediction Models: Enhancing Decision-Making Accuracy in Large-Scale Infrastructure Projects

Paulson Geo Philip

American Journal of Technology · 19.12.2024 · 3 (1) · 52-69

DOI: 10.58425/ajt.v3i1.571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Technology, online erschienen am 19.12.2024. Verfasst von Paulson Geo Philip. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

This research aims to design an artificial intelligence (AI)-based project risk prediction system to support more effective and flexible risk management practices for large-scale infrastructure projects, which are increasingly characterized by complexity, interdependence, inadequate performance, delays, and cost overruns.

Methods

The research is based on the findings of a systematic literature review and the conceptual application of AI across the infrastructure, energy, geotechnics, and oil and gas sectors. It examines the evolution of risk prediction methods from traditional expert- and statistics-based approaches to modern machine learning (ML) and deep learning (DL) techniques. The proposed framework integrates multiple AI approaches, including supervised, unsupervised, and reinforcement learning, as well as convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and transformers. The framework comprises an input layer, an AI-based analytics layer, a prediction layer, and a decision support layer.

Results

The research demonstrates that AI-based prediction systems can integrate multiple AI techniques to improve risk prediction, facilitate earlier risk identification, and enable continuous risk monitoring. Evidence from various fields indicates that AI techniques provide more accurate risk prediction than traditional methods. However, challenges related to data quality, model interpretability, AI and cybersecurity, and organizational resistance remain significant considerations in implementing AI-based risk management systems.

Conclusion

The study concludes that the application of AI in project risk management is highly justified despite implementation challenges. AI-based systems have the potential to transform infrastructure risk management by enabling early, data-driven, and intelligent decision-making in complex project environments. Recommendations: The study recommends the adoption of AI-based risk management systems for large-scale infrastructure projects to enhance risk prediction, early risk identification, continuous monitoring, and decision support, while addressing challenges related to data quality, model interpretability, cybersecurity, AI implementation, and organizational resistance.

Zitieren

APA

Philip, P. G. (2024). Artificial Intelligence-Driven Project Risk Prediction Models: Enhancing Decision-Making Accuracy in Large-Scale Infrastructure Projects. American Journal of Technology, 3(1), 52-69. https://doi.org/10.58425/ajt.v3i1.571

Vancouver

Philip PG. Artificial Intelligence-Driven Project Risk Prediction Models: Enhancing Decision-Making Accuracy in Large-Scale Infrastructure Projects. American Journal of Technology. 2024;3(1):52-69. doi:10.58425/ajt.v3i1.571

BibTeX
@article{Philip2024,
  author = {Philip, Paulson Geo},
  title = {Artificial Intelligence-Driven Project Risk Prediction Models: Enhancing Decision-Making Accuracy in Large-Scale Infrastructure Projects},
  journal = {American Journal of Technology},
  year = {2024},
  volume = {3},
  number = {1},
  pages = {52--69},
  doi = {10.58425/ajt.v3i1.571}
}
Kostenlos starten →