Abstract
The construction industry is characterized by complex projects, unpredictable outcomes and high risks of uncertainties impacting delivery, decision-making and efficiency. Neuro-fuzzy systems (NFS), which combine the adaptive learning capabilities of neural networks with the interpretability of fuzzy logic, present a transformative potential for enhancing decision-making and process optimization in construction. This study aims to investigate the key factors driving the adoption of NFS in the construction industry. The objective was achieved through a quantitative research approach using a well-structured questionnaire to collect data from construction professionals, including architects, quantity surveyors, builders, and engineers. Descriptive and inferential statistical methods, such as Exploratory Factor Analysis (EFA), Mean Item Score (MIS), and Standard Deviation (SD), were used for data analysis. The findings identified; enhanced communication networks, mobile device integration, responsiveness, efficiency and operational competence as the top drivers for adopting NFS. Findings from EFA categorized these drivers into three clusters: Output Factors, Peculiarity Factors and Preferential Factors. The findings of this study will serve as a reference for stakeholders, researchers and construction firms on the key drivers of NFS implementation in the construction industry. It will also contribute to the advancement of innovative technologies that support sustainable development in developing countries.
•The study unveils the key drivers and major clusters of Neuro-Fuzzy Systems (NFS) in the construction industry.•Reveals enhanced communication networks, mobile device integration, responsiveness, efficiency, and operational competence as the top drivers of NFS adoption.•CHighlights the potential of NFS in advancing innovative technologies for sustainable development in developing countries.•Provides strategic insights for construction stakeholders, SMEs, clients and decision-makers to leverage NFS to improve automation, skills and employment structures.