ABSTRACT:
Risk management is pivotal in decision-making and strategic planning in diverse fields, from finance to healthcare and construction management. Risk relief forecasting is crucial in various industries' strategic planning and budgeting processes. Accurate forecasting of the potential relief measures is essential for reducing negative impacts and optimizing contingency distribution for mitigating risks. The ample advancement in artificial intelligence applications helped researchers and practitioners to employ such advancements to serve multiple domains efficiently. Despite the importance of risk relief forecasting and the advancements in artificial intelligence, there is a noticeable lack of a comprehensive model to assess the efficiency of addressing the specific challenges for practical implementation in various industries. This gap in research hinders the full potential of AI-driven risk management solutions. This study introduces a novel approach using the Naïve Bayes algorithm to forecast risk relief in a categorized manner. The developed model presents a systematic approach for modeling the relief efficiency of risks based on the applied mitigation measures. Different scenarios are used to train the model, where a combination of independent mitigation strategies are the attributes that result in a specific category of efficiency for each of these scenarios. The historical mitigation strategies of similar projects along with their outputs are used to train the model and hence the model forecasting the relief efficiency of any combination of the proposed mitigation measures for the risks of the studied project. A case study has been used to validate the developed model. The model reveals an intelligent predictor can effectively forecast the categorized efficiency of risk relief. This approach demonstrates the capacity to improve decision-making and strategic planning in various sectors, eventually leading to more robust and competent risk management practices.
Presenter: Dr. Ashraf Salem, PhD, PEng, PMP, PMI-RMP
Ashraf is an Egypto-Canadian construction, mining, and transportation systems Senior Risk Manager and Project Controls professional engineer with over 20 years of experience in Design-Bid-Build (DBB), Design-Build (DB), Progressive Design- Build (PDB) and Public Private Partnership (PPP) civil engineering and infrastructure mega-projects. This involves planning, identifying, and performing qualitative and quantitative risk analysis from the conceptual to completion phases of the project. Specialized in EPCM project control management, procurement, cost, and schedule control, estimate review, risk reduction strategies, and change management. Ashraf has many publications with interests in innovative technologies and techniques in project and risk management.