Probabilistic Forecasting of Project Cost and Schedule Using Earned Value Management and Monte Carlo Simulation

Abstract

Accurate forecasting of project cost and schedule is essential for effective project control and decision-making. Traditional earned value management (EVM) offers a deterministic view of performance but fails to capture the uncertainties inherent in dynamic project environments. This study introduces a probabilistic forecasting approach that integrates EVM with Monte Carlo simulation to model the stochastic behavior of cost and schedule performance indices. Two hypothetical project scenarios are analyzed to demonstrate the method’s applicability: one characterized by cost efficiency but schedule delay, and another by schedule progress but cost overrun. In both cases, cumulative project data—planned value, earned value, and actual cost—are used to generate probabilistic estimates of cost and duration at completion, along with confidence intervals and risk profiles. The results show that the proposed framework produces smoother and more credible forecasts while quantifying the likelihood of budget and schedule outcomes. This enhances the interpretability and reliability of EVM by linking performance trends with uncertainty, offering project managers deeper insights for proactive and risk-informed decision-making.