Cost Predictive Model Adoption in Construction Organisations: A Pilot study
Abstract
Accurate construction cost estimation is essential for effective project planning, budgeting, and decision-making. The increasing complexity of construction projects has accelerated the adoption of advanced cost predictive models that complement traditional estimation techniques. However, limited empirical evidence exists regarding the acceptance and application of these predictive approaches within construction organisations. Therefore, this study aimed to examine the cost predictive model approaches adopted by construction organisations from the perspective of Quantity Surveyors. A quantitative research design was employed using a structured questionnaire survey distributed to Quantity Surveyors working in client, consultant, contractor, and subcontractor organisations. A total of 58 valid responses were analysed using descriptive statistics and the Kruskal–Wallis H test. The findings revealed that all seven cost predictive model approaches achieved a high level of agreement, indicating strong industry recognition of both conventional and advanced prediction techniques. Traditional Statistical Models recorded the highest mean score (M = 4.21), followed by Fuzzy Logic and AI-Based Models and Hybrid Models (M = 4.07), while Probabilistic and Bayesian Models obtained the lowest mean score (M = 3.76). Furthermore, the Kruskal–Wallis analysis indicated no statistically significant differences (p > 0.05) among respondents from different organisational categories, suggesting a common perception regarding the importance of cost predictive models across the construction industry. The study contributes to the growing body of knowledge on construction cost estimation by providing empirical evidence of practitioners' perceptions towards contemporary predictive approaches. The findings offer practical insights for construction organisations seeking to improve estimation accuracy and support the adoption of intelligent, data-driven cost prediction techniques as part of the industry's digital transformation.