Optimizing Project Time and Cost Prediction Using a Hybrid XGBoost and Simulated Annealing Algorithm

Abstract

Machine learning technologies have recently emerged as transformative tools for enhancing project management accuracy and efficiency. This study introduces a data-driven model that leverages the hybrid eXtreme Gradient Boosting-Simulated Annealing (XGBoost-SA) algorithm to predict the time and cost of construction projects. By accounting for the complexity of activity networks and uncertainties within project environments, the model aims to address key challenges in project forecasting. Unlike traditional methods such as Earned Value Management (EVM) and Earned Schedule Method (ESM), which rely on static metrics, the XGBoost-SA model adapts dynamically to project data, achieving 92% prediction accuracy. This advanced model offers a more precise forecasting approach by incorporating and optimizing features from historical data. Results reveal that XGBoost-SA reduces cost prediction error by nearly 50% and time prediction error by approximately 80% compared to EVM and ESM, underscoring its effectiveness in complex scenarios. Furthermore, the model’s ability to manage limited and evolving data offers a practical solution for real-time adjustments in project planning. With these capabilities, XGBoost-SA provides project managers with a powerful tool for informed decision-making, efficient resource allocation, and proactive risk management, making it highly applicable to complex construction projects where precision and adaptability are essential. The main limitation of the developed model in this study is the reliance on data from similar projects, which necessitates additional data for application to other industries.