Data fusion-based workforce prediction for capital projects: A framework with empirical case study

Abstract

Effective workforce planning is critical in transportation capital project delivery, particularly for agencies such as local and state departments of transportation (DOTs). Traditional methods, relying on empirical approaches to estimate personnel resource requirements from experienced engineers, often fall short in terms of accuracy and scalability. This study proposes a novel data-fusion-based prediction framework for capital project workforce estimation. Leveraging past project and accounting data, the framework provides an automatic data pipeline that considers the impact of project location, project scale, project type, and project complexity. The proposed framework is empirically validated through a case study that utilized the New York State Department of Transportation (NYSDOT) project and accounting database. The results suggest this innovative approach improves staffing decisions, promotes efficient resource allocation, fosters cross-regional collaboration, and aids agency leadership in assessing their project delivery teams’ effectiveness. The benefits and applicability of the framework can be easily extended to federal, state, county, and local municipal agencies tasked with delivering capital projects.

Keywords

• Capital project management
• Workforce prediction
• Data-fusion model
• Resource allocation