Year: 2025
Type: article
Abstract: Accurate construction cost estimation is crucial for effective project planning and resource management in the construction industry. Traditional estimation methods often suffer from inaccuracies due to the complexity and variability of construction projects. This study explores the application of regression-based machine learning models support vector machine (SVM), K-nearest neighbours (KNN), and multilayer perceptron (MLP) to improve the precision of construction cost predictions. The study evaluates the performance of these models using a construction-related dataset that includes factors such as material costs, labour expenses, and project characteristics. The results revealed that the SVM model outperforms the others, achieving an RMSE of 18,189 and an R2 of 0.975, indicating its superior ability to predict construction costs accurately. The KNN and MLP models also demonstrated effectiveness, but with higher errors, particularly in more complex data scenarios. This research highlights the potential of machine learning techniques to revolutionise construction cost estimation, providing more reliable, data-driven insights for project planning and budgeting.
Author: Yanfei Shen
Institution: Sanmenxia Polytechnic
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4411242367