Probabilistic Scheduling Based On Hybrid Bayesian Network–Program Evaluation Review Technique,

Project scheduling based on probabilistic methods commonly uses the Program Evaluation Review Technique (PERT). However, practitioners do not widely utilize PERT-based due to difficulty in obtaining historical data for similar projects. PERT has several drawbacks, such as inability update activity dura- tions real time. In reality, changes project conditions related resources have a highly dynamic nature. The availability of materials, fluctuating labor productiv- ity, and equipment significantly determine completion This research aims propose model Hybrid Bayesian Network-PERT. combines with Network (BN). BN is used accommodate real-time resource conditions. modeling diagrams variables obtained through an in-depth literature review, direct field observations, distributing questionnaires experts scheduling. validated by applying proposed 60 m concrete bridge construction Indonesia. simulation results are then compared case study assess model’s accuracy. result shows that hybrid Bayesian-PERT accurate can eliminate weaknesses method. Besides being able provide prediction time (93.4%), this also be updated according actual condition