Risk-based cost estimation in construction by employing machine learning techniques

Abstract

The construction industry is one of the sectors that experiences frequently cost overruns. Therefore, precise cost estimation for the completion of construction projects is essential. Several research studies focus on cost estimation, construction risk parameters, and their monetary effects. While they developed significant predictive models for project completion costs, they mainly focused on the initial construction phases. Estimating the completion cost accurately in the early phases of construction projects is critical to their success. However, cost overruns are almost inevitable due to the risks inherent in construction projects. Hence, the completion cost fluctuates throughout the execution phase and requires periodic updates. Limited studies have developed methodologies for estimating completion costs throughout the execution phase of projects. However, their models do not incorporate the implications of total risk scores. Further study is required to examine risk-based cost prediction for completion throughout the construction execution phase. There is a need for a prompt and user-friendly completion cost estimation model that accounts for fluctuating risk scores and their impact on the total cost during the execution phase. Machine learning (ML) techniques could address these requirements by providing effective methods for tackling dynamic systems. The proposed approach includes ML prediction and classification models to estimate total completion cost and cost overrun percentage class of the project, respectively. Within the predictive models, six predictive algorithms were utilized, employing machine learning techniques. Analysis of the outputs revealed that polynomial regression yielded the most precise predictions for the supplied data from globally operating construction company. The classification approach aims to predict the cost overrun ratio classes of the completion cost according to the changes in the total risk scores at any time of the project. Six classification algorithms were utilized and validated by employing data points from a globally operating construction company. The performances of the algorithms were evaluated with validation and performance indices. The decision tree classifier surpassed other algorithms. The main objective of this study is to provide a system that predicts the total completion cost and/or cost overrun percentage classification based on the total risk score of projects at any point of the execution phase. Although there are some research limitations, including risk perception, data gathering restrictions, and selecting proper ML algorithms upon data properties, this research improves the planning abilities of construction executives by providing completion cost and cost overrun ratio based on changing total risk scores, facilitating swift and simple assessments at any stage of a construction project's execution.