Machine learning models as a budget validation method for U.S. mass-transit projects
Capital budgets for U.S. mass transit projects have consistently been underestimated. The resulting budget overruns cause funding challenges for urban transit authorities and the Federal Transit Administration. Developing accurate budget estimates is a significant challenge for project managers, particularly given the influence of cognitive biases such as optimism bias. This quantitative study analyzed data from 108 projects using two machine learning models to predict actual project costs. The results demonstrated a budget validation process employing statistical software, objective variables, and machine learning methods, yielding statistically significant outcomes.
Authors
- Paul Boudreau (ORCID: https://orcid.org/0009-0004-2338-1042)
Institutions
- National University (PH)
- National University (US)
Publication Details
- Journal
- Transportation Research Interdisciplinary Perspectives
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1016/j.trip.2026.102359
- Primary Topic
- Construction Project Management and Performance
- Type
- article
- Field-Weighted Citation Impact
- 0.00