Integrating Big Data and Knowledge Management for Intelligent Risk Prediction in Engineering Projects

Abstract

With the rise of big data, engineering schedule risk management has new opportunities to enhance decision-making and efficiency, yet accurate and timely risk identification remains a challenge. This paper reviews current big data-based models and highlights their limits in accuracy, responsiveness, and practical use. The authors propose a dynamic, knowledge-driven prediction model integrating multi-source data for real-time risk perception and early warning. Validated through a simulated case, the model improves risk identification and adaptive control. Emphasis is placed on bridging theory and practice to enhance knowledge utilization. Findings show that combining big data with knowledge management boosts organizational resilience and supports intelligent decisions. This study contributes to smart knowledge systems and offers actionable insights for improving engineering risk management.