Predictive Analytics for Construction Material Procurement, Cost Control and Schedule Performance in Saudi Giga-Projects

Unprecedented construction activity, tight delivery windows, complex interfaces, global sourcing, and exposure to volatile material markets characterize Saudi Arabia’s giga-project portfolio. These conditions make procurement, cost control, and schedule performance highly interrelated. This review critically discusses how predictive analytics can convert fragmented project, commercial, supply-chain, and progress data into forward-looking decisions for construction material procurement for Saudi giga-projects. An integrative review method integrates recent peer-reviewed evidence on machine learning, construction cost forecasting, schedule prediction, digital supply chains, building information modeling, digital twins, and Saudi project performance. The literature indicates that the predictive value is greatest when models combine material demand, price escalation, supplier reliability, lead times, inventory status, progress quantities, and schedule logic, rather than attempting to predict a single outcome in isolation. Ensemble learning and hybrid models regularly yield better forecasting precision, but their operational-level usefulness depends on data quality, temporal validity, explainability, and integration with procurement and project-control workflows. Saudi studies consistently identify material-price fluctuation, change orders, planning weaknesses, and delayed approvals as major cost and time pressures. Yet, direct evidence of analytics-enabled procurement in giga-project settings remains limited. The review suggests an integrated predictive-control architecture that links 5D BIM, enterprise resource planning, supplier data, market indicators and planning systems. It argues that predictive analytics in giga-project organizations should be seen as a governance capability rather than a standalone algorithm, marrying model outputs with human review, uncertainty ranges and auditable intervention thresholds. Future research directions encompass Saudi longitudinal datasets, cross-project transferability, causal evaluation of interventions, supplier-risk prediction, and explainable models that jointly optimize procurement cost, material availability, and schedule resilience.