Integrating expert insights and data analytics for enhanced construction productivity monitoring and control: a machine learning approach

Abstract

Purpose

This study aims to enhance productivity monitoring and control in the construction industry by integrating data-driven analytics with expert insights.

Design/methodology/approach

A novel framework combines expert knowledge and data analysis to identify productivity trends and devise improvement strategies. A machine learning model predicts productivity ranges using historical data and project-specific factors’ evaluated by surveys, supported by a warning dashboard for proactive decision-making.

Findings

The findings reveal that integrating expert insights with data analytics significantly enhances the ability to monitor and control productivity, leading to proactive strategies for construction stakeholders. The machine learning model demonstrates robust accuracy in forecasting productivity ranges, allowing for early identification of potential issues. The dashboard system proves invaluable, offering semi-real-time alerts and facilitating swift action to prevent productivity lapses. These results highlight the effectiveness of the proposed approach in detecting trends, predicting outcomes and enabling timely interventions, thereby contributing to the overall productivity improvement of construction projects.

Research limitations/implications

There are also limitations to consider, including potential data availability, constraints in the expert pool, implementation challenges and the need for long-term evaluation; these factors should be considered when interpreting the study’s findings and applying the proposed framework to construction projects. Future research can focus on expanding the application of this framework to different types of construction projects and evaluating its scalability.

Practical implications

This study introduces a framework with a warning dashboard for early detection of issues, combining expert insights and data analysis for improved project outcomes. This research suggests a shift toward more expert, data-driven, insightful decision-making in construction, aiming for enhanced performance and reduced disruptions. An important implication of this research is the need to balance digital tools and expert judgment. Project managers are advised to use a holistic strategy that ensures informed and comprehensive decision-making.

Originality/value

This research introduces a unique methodology that blends traditional expertise with modern analytics to address construction productivity challenges. It offers a practical solution for stakeholders to enhance decision-making, resource allocation and project planning, marking a significant contribution to construction management literature.

Citation

Pourrahimian, E., Eltahan, A., Salhab, D., Crawford, J., AbouRizk, S. and Hamzeh, F. (2024), "Integrating expert insights and data analytics for enhanced construction productivity monitoring and control: a machine learning approach", Engineering, Construction and Architectural Management, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/ECAM-02-2024-0268