Modeling Performance and Uncertainty of Construction Planning under Deep Uncertainty: A Prediction Interval Approach

In construction planning, decision making has a great impact on final project performance. Hence, it is essential for managers to assess the planning and make informed decisions. However, disproportionately large uncertainties occur during stage; in worst case, reliable probability distributions of are sometimes unavailable due lack information before implementation. This situation constitutes deep uncertainty problem, challenge perform probability-based assessment. The current study proposes modeling approach that applies prediction intervals via integration discrete-event simulation (DES), fuzzy C-means clustering (FCM), Bayesian regularization backpropagation neural networks (BRBNNs), particle swarm optimization (PSO). DES used data sampling alternatives their performances under uncertainty. Based generated samples, FCM, BRBNN, PSO integrated machine learning algorithm model represent relationships between schemes, performances, corresponding uncertainties. proposed was applied case project, with results indicating capable performance defined 95% confidence level fluctuation within 1~9%. presented research contributes new innovative option, using solve problems, without relying demonstrates effectiveness planning.