Developing an Integrated Artificial Intelligence-Driven Framework for Predictive Risk Management in Complex Projects: An Applied Approach to Improving Project Time, Cost, and Quality
Developing an Integrated Artificial Intelligence-Driven Framework for Predictive Risk Management in Complex Projects: An Applied Approach to Improving Project Time, Cost, and Quality
Mohammadreza Rajabi1
1) Master s student in Project Management - Ivanki Non-Profit University
IOI Code
:
ACCD-ABKHDE
Publication :
10th International Conference on Applied Researches in Science & Engineering (carseconf.com)
Abstract :
The increasing complexity of projects, growing uncertainty, resource constraints, and the need for timely and accurate decision-making have made risk management a critical component of project success. Although traditional risk management approaches remain valuable, they face limitations when dealing with large volumes of data, complex interdependencies, and rapidly changing project environments. Artificial Intelligence (AI), through capabilities such as machine learning, predictive analytics, natural language processing, and generative AI, offers significant opportunities for transforming project risk management.
This study aims to develop an integrated Artificial Intelligence-driven framework for predictive risk management in complex projects. An applied analytical research approach is adopted through the review and synthesis of scientific literature addressing Artificial Intelligence, project management, and project risk management. Recent systematic reviews have demonstrated that AI techniques can support project risk assessment, cost estimation, duration forecasting, planning, execution, and monitoring.
Based on the literature analysis, the proposed framework consists of six major stages: project data acquisition, intelligent risk identification, risk prediction, risk assessment and prioritization, response strategy selection, and continuous risk monitoring. Within this framework, Artificial Intelligence is considered a decision-support capability rather than a replacement for project managers. Data quality, organizational readiness, human competencies, model interpretability, and human oversight are incorporated as key enabling factors.
The proposed framework provides a structured pathway for organizations to move from reactive risk management toward predictive and data-driven project risk management. By integrating AI capabilities with professional project management expertise, the framework can support improved control of project time, cost, and quality and provide a practical foundation for future empirical validation.
Keywords : artificial intelligence project management project risk management predictive risk management complex projects predictive analytics project performance