Quantifying, Forecasting, and Mitigating Construction Labor and Material Challenges in a Dynamic Global Economy Using Econometrics and Deep Learning

Author

• Ahmed Gamal Elsayed Mohamed Shiha, Missouri University of Science and Technology

Abstract

"The construction industry contributes to the global economy, yet its cost management practices remain constrained by labor shortages and material price volatility. These challenges are intensified by economic disruptions, geopolitical tensions, and trade policy shifts. Despite a growing body of literature, five knowledge gaps remain unaddressed: (1) the absence of dynamic, and localized measures of construction labor shortages; (2) limited empirical investigation of macroeconomic leading indicators of labor shortages; (3) underutilization of deep learning (DL) algorithms in forecasting local construction labor earnings; (4) the limited treatment of structural breaks in existing construction material price forecasting models; and (5) the lack of an empirical framework that quantifies the impacts of import volume fluctuations on the prices of construction materials. This research develops a quantitative framework, structured in five research modules, to address these gaps. Module 1 develops a dynamic labor shortage index at the metropolitan statistical area level. Module 2 identifies macroeconomic leading indicators of construction labor shortages across 28 North American and 17 European markets. Module 3 develops DL-based forecasting models for state-level labor earnings. Module 4 investigates whether macroeconomic indicators of the trading partners can serve as leading indicators of domestic material prices. Module 5 quantifies the impacts of import volume fluctuations on construction material prices. This research establishes a reproducible, and decision-relevant framework that empowers stakeholders to anticipate and mitigate the financial risks associated with labor shortages and material price volatility in dynamic economic environments"-- Abstract, p. iii

Advisor(s)

El-adaway, Islam H.

Committee Member(s)

Ashuri, Baabak
Myers, John J.
Paige, Robert L.
Schonberg, William P.

Department(s)

Civil, Architectural and Environmental Engineering

Degree Name

Ph. D. in Civil Engineering

Publisher

Missouri University of Science and Technology

Publication Date

2026

Pagination

xvi, 375 pages

Note about bibliography

Includes_bibliographical_references_(pages 342-372)

Rights

© 2026 Ahmed Gamal Elsayed Mohamed Shiha , All Rights Reserved

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12626

Recommended Citation

Shiha, Ahmed Gamal Elsayed Mohamed, "Quantifying, Forecasting, and Mitigating Construction Labor and Material Challenges in a Dynamic Global Economy Using Econometrics and Deep Learning" (2026). Doctoral Dissertations. 3472.
https://scholarsmine.mst.edu/doctoral_dissertations/3472