CONSTRUCTION SCHEDULE RISK ANALYSIS – A HYBRID MACHINE LEARNING APPROACH

Abstract

The UK commissions about £100 billion in infrastructure construction works every year. More than 50% of them finish later than planned, causing damage to the interests of stakeholders. Planning for the inherent uncertain and unknown factors in these projects is a challenging practice. The estimation of time-risk on construction projects is done subjectively, largely by experience despite there are many existing techniques available to analyse risk on the construction schedules. Being one of the most widely used with risk analysis techniques, the Monte Carlo method and its variants can only analyse a small number of projects and are based on expert opinion alone. Unlike conventional methods that tend to depend on the accurate estimation of risk boundaries for each task, this research aims to explore a hybrid method to assist planners in undertaking risk analysis using baseline schedules with improved accuracy. The proposed method is endowed with machine intelligence and is trained using a database of 293,263 tasks from a diverse sample of 302 completed infrastructure construction projects in the UK. It combines a Gaussian Mixture Modelling-based Empirical Bayesian Network and a Support Vector Machine followed by performing a Monte Carlo risk simulation. The former is used to investigate the uncertainty, correlated risk factors, and predict task duration deviations while the latter is used to return a time-risk simulated prediction. The testing results on 10 trial projects demonstrate that our proposed method outperforms the state-of-the-art. We acquired a significant improvement in the prediction accuracy by 54.4%.