Construction schedule risk analysis – a hybrid machine learning approach

The UK commissions about £100 billion in infrastructure construction works every year. More than 50% of them finish later planned, causing damage to the interests stakeholders. estimation time-risk on projects is currently done subjectively, largely by experience despite there are many existing techniques available analyse risk schedules. Unlike conventional methods that tend depend accurate boundaries for each task, this research aims proposes a hybrid method assist planners undertaking analysis using baseline schedules with improved accuracy. proposed endowed machine intelligence and trained database 293,263 tasks from diverse sample 302 completed UK. It combines Gaussian Mixture Modelling-based Empirical Bayesian Network Support Vector Machine followed performing Monte Carlo simulation. former used investigate uncertainty, correlated factors, predict task duration deviations while latter return simulated prediction. This study randomly selected 10 as case studies comparing their results Simulation. Results indicated 54.4% more prediction project delays.