Advanced Machine Learning Framework for Predicting BIM User Satisfaction

Strategic Insights -

A study conducted by researchers from National Yang Ming Chiao Tung University in Taiwan has developed an advanced machine learning framework for predicting building information modeling (BIM) user satisfaction. The framework integrates the forensic-based investigation (FBI) algorithm with gradient boosting machine, light gradient boosting machine, adaptive boosting (AdaBoost), extreme gradient boosting, and random forest algorithms to accurately predict BIM user satisfaction. The research aims to enhance the implementation and user experience of BIM technologies in construction projects.

Key Takeaways:

  • The study conducted a comprehensive survey on 70 construction projects in Taiwan that used BIM technologies to support design work.
  • The synthetic minority oversampling technique (SMOTE) was integrated into the proposed models to address the data imbalance problem.
  • The FBI-AdaBoost-SMOTE model exhibited the highest performance, achieving accuracy, precision, recall, and F1 scores of 88.6%, 90.6%, 88.6%, and 87.8%, respectively.
  • The FBI-AdaBoost model based on Shapley additive explanations identified contextual analysis and visualization, project scale, and cost estimates as key determinants of BIM user satisfaction.
  • The study presents an advanced machine learning framework for predicting BIM user satisfaction and identifying key influencing factors for BIM user satisfaction.
  • The research has been peer-reviewed and published in the journal Applied Soft Computing.
  • The study highlights the potential of predictive modeling for optimizing the adoption of BIM in the architecture, engineering, and construction industry.

Statistics:

  • 70 construction projects in Taiwan participated in the comprehensive survey.
  • The proposed models achieved accuracy, precision, recall, and F1 scores of 88.6%, 90.6%, 88.6%, and 87.8%, respectively.
  • The study integrated the synthetic minority oversampling technique (SMOTE) to address the data imbalance problem.

Sources:

  • Measuring Building Information Modeling User Satisfaction By Using Active Interpretable Machine Learning. Applied Soft Computing, 2025;183.
  • Elsevier. Applied Soft Computing. (www.journals.elsevier.com/applied-soft-computing/)
  • NewsRx. New Findings Reported from Department of Civil Engineering Describe Advances in Machine Learning (Measuring Building Information Modeling User Satisfaction By Using Active Interpretable Machine Learning). Information Technology Newsweekly. November 4, 2025; p 379.