Time Series Forecasting in Construction Management: A Scientometric Analysis, Qualitative Review, and Future Research

Abstract

The increasing availability of construction data and advances in artificial intelligence (AI) have accelerated the adoption of time series forecasting across construction management. However, a comprehensive understanding of the field’s knowledge structure, methodological evolution, and future directions remains limited. To address this gap, a scientometric and qualitative review was conducted on 192 journal articles published between 2010 and December 2025 and retrieved from the Web of Science Core Collection and Scopus databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. VOSviewer was employed to visualize the knowledge structure, collaboration networks, and research themes. The results indicate sustained growth in research activity since 2010, accompanied by increasing international collaboration. Six major research streams were identified: cost estimation and forecasting, safety and risk management, schedule and performance monitoring, productivity and resource management, sustainability and waste management, and emerging methods and future technological directions. The findings reveal a clear transition from traditional statistical approaches, including AutoRegressive Integrated Moving Average (ARIMA) and vector error correction (VEC) models, toward machine learning, deep learning, and hybrid forecasting frameworks. At the same time, traditional methods remain important because of their interpretability and practical applicability. Three persistent challenges were identified: data quality and availability, model interpretability, and practical implementation. Future research is expected to focus on lightweight real-time forecasting, multimodal data fusion, explainable AI, and physics-informed forecasting models. This review provides an integrated understanding of the field and a research agenda for future methodological and practical development. For practitioners, it further highlights that the value of forecasting models depends not only on predictive accuracy but also on interpretability, computational efficiency, data requirements, and practical deployability in construction decision-making.