Financial and Economic Risk Analysis in Construction Projects Leveraging Big Data and Artificial Intelligence

Over the past decade, the construction industry has faced increasing financial uncertainties due to cost overruns, schedule delays, and volatile economic conditions. Traditional risk assessment models, which rely heavily on static historical data and expert judgment, often fail to capture the dynamic and complex interactions inherent in large-scale construction projects. This study proposes an integrated financial and economic risk analysis framework that leverages Big Data analytics and artificial intelligence (AI) techniques to enhance predictive accuracy and decision-making in construction project management. Drawing on a comprehensive dataset comprising project financial statements, cost breakdowns, environmental factors, and market indicators, we apply advanced machine learning algorithms to identify hidden risk patterns and model potential cost escalations. The methodology involves feature engineering, predictive modeling using ensemble methods, and validation through cross-industry case studies. Findings reveal that AI-driven models outperform conventional approaches in early detection of financial risks, particularly in fluctuating market contexts. Moreover, integrating economic indicators improves the robustness of risk forecasts, enabling more resilient budgeting and financing strategies. This research contributes to both the construction management and financial accounting literature by providing a data-driven, interdisciplinary approach to risk evaluation. The proposed framework offers practical implications for contractors, investors, and policymakers aiming to reduce financial exposure and improve project sustainability.

کلیدواژه ها:

Big Data Analytics ، Artificial Intelligence ، Construction Project Finance ، Risk Assessment ، Economic Forecasting