Update of the ARDOT Workforce Forecasting System

Details

• Creators:
  Mitra, Suman ; Hernandez, Sarah ; Ogungbire, Adedolapo ; Mullin, Erin ; Sexton, Clayton
• Corporate Creators:
  University of Arkansas, Fayetteville. Department of Civil Engineering
• Corporate Contributors:
  United States. Department of Transportation. Federal Highway Administration ; Arkansas. Department of Transportation. Transportation Research Committee
• Subject/TRT Terms:
  Forecasting Planning Software Workforce
• Publication/ Report Number:
  TRC2101
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  Arkansas. Department of Transportation. Transportation Research Committee
• Abstract:
  This report assesses the existing manpower forecasting tool used for workforce allocation and provides a comprehensive description of the development of a new, modern forecasting system. An extensive review of existing tools and state-of-the-art methods for similar forecasting was conducted, including the identification of key factors influencing manpower forecast planning. Historical data were retrieved and analyzed to better understand past workforce requirements, and regression models were developed based on this data. Distribution models were created to estimate workforce utilization over the lifespan of projects and by the job types available in the data. Specialized regression models were developed using work types and grouping similar work types for insufficient project listings, and a methodology for forecasting was integrated into the backend of a web application. Extract, Transform, Load (ETL) capabilities were implemented within the software system, and a user-friendly front-end application was developed to ensure smooth access for users. Recommendations are made to monitor key factors established to influence the workforce on projects for future system improvements. Additionally, it is recommended that more data be made available to the system to enable the possibility of more advanced models, which current data limitations hinder.
• Format:
  PDF
• Funding:
  TRC2101
• Collection(s):
  US Transportation Collection
• Main Document Checksum:
  urn:sha-512:ba696093cb4631a3a4a4b66f050eac3b747aaa0ddcb46260f67f19a2d654f5e997e0c8555405962294565f9963f1aaf7f2b5be6710a705d71636979fc4ebf123
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/92059/dot_92059_DS1.pdf
• File Type:
  [PDF - 2.79 MB ]