Machine Learning in Construction: A Systematic Review with a Focus on Nigeria

The Nigerian construction industry faces persistent challenges, including inefficiencies, delays, and cost overruns, which significantly limit its contribution to national development. Globally, machine learning (ML) has revolutionized the construction sector by improving processes such as cost estimation, project scheduling, and risk management. Despite its potential, ML adoption in Nigeria remains minimal, with significant gaps in research and application. This study seeks to address this gap by conducting a systematic review of ML applications in the global construction industry, with a focused analysis of opportunities and barriers for implementation within the Nigerian context. A systematic review methodology was adopted, following PRISMA guidelines. Relevant peer-reviewed articles were sourced from databases such as Scopus and Google Scholar, and thematic analysis was conducted to compare global trends with the Nigerian construction landscape. Key findings reveal that ML has enhanced project efficiency, optimized costs, and facilitated data-driven decision-making globally. Specific opportunities for ML adoption in Nigeria include resource optimization through efficient allocation of materials and labor, predictive maintenance for minimizing equipment downtime and repair costs, and advanced data-driven project management to improve planning and execution. However, barriers such as economic instability, limited technical expertise, and infrastructure deficiencies hinder widespread adoption. This study recommends targeted strategies, including investments in ML capacity building through specialized training, infrastructure development, and fostering collaborations between academia and industry. Accelerating ML adoption is essential for enhancing the competitiveness, efficiency, and sustainability of Nigeria’s construction industry, thereby contributing to broader national development objectives. Future research should focus on empirical investigations to validate these findings and provide actionable insights for implementing ML in Nigeria’s construction sector.