A Systematic Review of Data Analytics Applications in Construction Project Management

Abstract

The construction industry is experiencing rapid digital transformation as projects generate increasingly large and complex datasets. Traditional project management methods often struggle to process and utilize this information effectively, creating a growing need for data-driven approaches. This systematic review examines current applications of data analytics in construction project management by analyzing research from major scientific databases. Findings indicate that analytics is widely applied in cost estimation, schedule forecasting, safety monitoring, productivity assessment, risk analysis, resource allocation, equipment tracking, and quality control. Common techniques include machine learning, predictive analytics, statistical modeling, simulations, and big-data frameworks. Despite these advancements, challenges such as data fragmentation, lack of standardization, limited integration across project phases, and skill shortages hinder widespread adoption. The review highlights opportunities for future research to support a more intelligent, data-driven construction industry.