Risk-supported case-based reasoning approach for cost overrun estimation of water-related projects using machine learning

Abstract

PurposeThe present study aims to develop a risk-supported case-based reasoning (RS-CBR) approach for water-related projects by incorporating various uncertainties and risks in the revision step.Design/methodology/approachThe cases were extracted by studying 68 water-related projects. This research employs earned value management (EVM) factors to consider time and cost features and economic, natural, technical, and project risks to account for uncertainties and supervised learning models to estimate cost overrun. Time-series algorithms were also used to predict construction cost indexes (CCI) and model improvements in future forecasts. Outliers were deleted by the pre-processing process. Next, datasets were split into testing and training sets, and algorithms were implemented. The accuracy of different models was measured with the mean absolute percentage error (MAPE) and the normalized root mean square error (NRSME) criteria.FindingsThe findings show an improvement in the accuracy of predictions using datasets that consider uncertainties, and ensemble algorithms such as Random Forest and AdaBoost had higher accuracy. Also, among the single algorithms, the support vector regressor (SVR) with the sigmoid kernel outperformed the others.Originality/valueThis research is the first attempt to develop a case-based reasoning model based on various risks and uncertainties. The developed model has provided an approving overlap with machine learning models to predict cost overruns. The model has been implemented in collected water-related projects and results have been reported.

A heuristic approach of modelling developing countries' construction sector uncertainties to improve the building environment

“…Other authors (Frimpong and Oluwoye, 2003;Vu et al, 2016;Bilal et al, 2019;Liu, 2019;Ndunguru et al, 2020;Sohrabi and Noorzai, 2022) have also investigated independently the causes of the latter to describe and identify, in order of importance, the upstream positions where the most fear should be made. All these studies remain conceptual, where the relative contributions of the causes to each other are obtained, but there is still no mathematical tool to calculate these uncertainties or their interactions.…”

“…The use of IT tools is essential to lighten the calculation of variations in costs and delays caused by previous enumerated factors (Bilal, 2019;Fandjio Yonzou et al, 2022;Sohrabi and Noorzai, 2022) as digital technologies, which are based on proven mathematical formulae (Hou et al, 2022). Thanks to linear optimization based on the calculation of workers' yields, Kouamou et al (2016) set up an enterprise resource planning (ERP) that allows, on one hand, to calculate the optimal size of the workforce and, on the other hand, to generate a dynamic work schedule, according to the available workforce.…”