Journal of Civil Engineering and Management | 2026
Authors: Lee K.-T.; Shin S.-H.; Choi J.-B.I.H.; Kim J.-H.
DOI: 10.3846/jcem.2026.26811
Journal: Journal of Civil Engineering and Management
Year: 2026
Publisher: Vilnius Gediminas Technical University
Document Type: Article
Open Access: All Open Access; Gold Open Access; Green Open Access
Cited by: 0
International market selection (IMS) plays a pivotal role in shaping construction companies’ global strategies. However, conventional IMS models generally fail to capture the distinctive challenges in the construction sector, such as the regulatory volatility, supply chain vulnerabilities, and site-specific operational constraints. To address these deficiencies, this study introduces a data-driven IMS framework specifically designed for the construction industry that incorporates financial, institutional, and industry-specific variables. The research adopts a two-phase analytical process: First, key IMS factors are identified and assessed through four methodological approaches, namely, logistic regression, partial least squares structural equation modeling, adaptive neuro-fuzzy inference systems (ANFIS), and the fuzzy ordinal priority approach. Second, the model is validated using 5,656 international market entry records for Indian construction firms from 2016 to 2023. The results demonstrate that the proposed artificial intelligence-enhanced framework significantly outperforms conventional models. Specifically, the ANFIS model achieved a prediction accuracy of 94.523% with an AUC-ROC of 0.874. This quantitative enhancement confirms that the integrated approach effectively captures nonlinear interactions and complex market constraints that conventional models generally neglect. Internal variables such as international experience and engineering productivity contribute positively to predictive accuracy. Meanwhile, external variables, particularly geographic distance and national risk, are demonstrated to be more difficult to model. Overall, the proposed framework provides a reliable foundation for strategic decision-making in global construction. It provides actionable insights for firms aiming to expand sustainably in uncertain international environments. © 2026 The Author(s).
adaptive neuro-fuzzy inference system; artificial intelligence; data-driven decision making; international construction project; international market selection model