Cost Optimization in Construction SMEs: An AI-Based Approach to Procurement and Budget Control

Abstract

In construction project management, small and medium-sized enterprises (SMEs) face significant financial risks due to volatile material prices, limited bargaining power, and weak cost-control mechanisms. This study proposes an AI-based integrated framework for cost and contract management. In the pre-construction phase, it evaluates contractors’ bills of quantities (BOQs) using AI-driven analysis to guide contractor selection. Once a contractor is chosen, the system integrates with change order and invoicing processes to track amounts, commitments, and estimates in real time while proactively flagging risks. Post-construction, it monitors invoices against actual progress, preventing duplicates and ensuring compliance with AIA invoice requirements, sworn statements, and conditional waivers, thereby reducing cash flow disruptions and project delays. The framework also includes an AI-driven cost optimization engine that leverages regression and clustering techniques to detect procurement inefficiencies, benchmark suppliers, and recommend corrective strategies. Validation on real project datasets demonstrates measurable reductions in budget variance - the difference between the approved budget and estimated project cost at completion - and overall project expenditures. Compared with manual estimation, the AI-driven approach delivers higher accuracy, actionable insights, and significant cost savings. Overall, this framework enhances SMEs’ efficiency in cost and invoice management, strengthens competitiveness, reduces financial risks, and supports broader participation in infrastructure projects.