Stochastic Cost Estimation in Transportation Infrastructure Projects Using Monte Carlo Simulation and Correlated Risk Variables

Peru faces critical challenges in the development and maintenance of its national road infrastructure, comprising over 32,000 km, of which only 26% are classified as being in good condition. This infrastructural deficit significantly elevates logistics costs and undermines national competitiveness, particularly in key sectors such as agriculture and mining. In this context, improving the accuracy and reliability of cost estimation in road infrastructure projects is imperative to optimize resource allocation and mitigate the risk of cost overruns. This study proposes a stochastic cost estimation framework that integrates Monte Carlo simulation with correlation matrices, enabling the modeling of uncertainty and the complex interdependencies among critical cost drivers. The methodology was applied to the Oyon Ambo highway in Peru. Historical input cost databases were analyzed to define probabilistic distributions, and correlation coefficients were employed to represent the dependencies between variables such as material prices, labor productivity, and equipment efficiency. The stochastic model produced probabilistic cost forecasts with associated confidence intervals and quantified risk exposure. The findings demonstrate that the proposed integrated approach significantly enhances the precision and robustness of cost estimates, providing project managers and decision-makers with a rigorous, data-driven tool for risk-informed budgeting and strategic financial planning in complex infrastructure projects.