Predictive Cost-Risk Analytics and Construction Supply Chain Resilience for Saudi Giga-Projects: A Framework for Early Warning, Forecasting and Procurement Decision-Making

Saudi Arabia’s giga-project portfolio concentrates exceptional capital, schedule pressure, supplier interdependence and exposure to volatile markets within programmes expected to deliver strategic outcomes under Vision 2030. Conventional cost control and procurement reporting are necessary but often backward-looking: they describe variance after commitments, disruptions or productivity losses have already materialised. This review develops an evidence-informed framework for predictive cost-risk analytics and construction supply chain resilience that shifts management attention towards earlier signals, probabilistic forecasts and procurement interventions. Thirty peer-reviewed sources published from 2020 to 2025 were synthesised across construction cost prediction, cost-risk modelling, digital twins, construction supply chain management, resilience, robust optimisation and Saudi digital transformation. The evidence indicates that useful early warning requires more than a single machine-learning model. It depends on a governed data architecture that connects quantities, schedules, commitments, supplier performance, market indices, logistics events and site progress; combines statistical, machine-learning and scenario-based forecasts; and translates risk states into explicit procurement responses. Supply chain resilience is strengthened when visibility is paired with options such as back-up sourcing, inventory buffers, package resequencing, alternative logistics and contract mechanisms. Digital twins can improve the temporal connection between physical progress, cost exposure and supply conditions, but fragmented data, inconsistent coding, model drift and weak organisational response can undermine technical capability. The review proposes a six-layer Predictive Cost-Risk and Resilient Procurement Framework comprising data integration, baseline intelligence, predictive modelling, early-warning governance, procurement decision support and outcome learning. For Saudi giga-projects, the framework supports earlier intervention, more defensible contingency allocation and more resilient procurement decisions without displacing professional judgement.