PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
The Adoption of a Machine Learning Approach in a Big Data Concept to Predict Project Cost Budgeting in the Thai Auction Process of Procurement Management for a Construction Project
Version 1
: Received: 6 June 2023 / Approved: 7 June 2023 / Online: 7 June 2023 (10:50:29 CEST)
Version 2
: Received: 17 July 2023 / Approved: 2 August 2023 / Online: 3 August 2023 (10:55:35 CEST)
Kusonkhum, W.; Srinavin, K.; Chaitongrat, T. The Adoption of a Big Data Approach Using Machine Learning to Predict Bidding Behavior in Procurement Management for a Construction Project. Sustainability2023, 15, 12836.
Kusonkhum, W.; Srinavin, K.; Chaitongrat, T. The Adoption of a Big Data Approach Using Machine Learning to Predict Bidding Behavior in Procurement Management for a Construction Project. Sustainability 2023, 15, 12836.
Kusonkhum, W.; Srinavin, K.; Chaitongrat, T. The Adoption of a Big Data Approach Using Machine Learning to Predict Bidding Behavior in Procurement Management for a Construction Project. Sustainability2023, 15, 12836.
Kusonkhum, W.; Srinavin, K.; Chaitongrat, T. The Adoption of a Big Data Approach Using Machine Learning to Predict Bidding Behavior in Procurement Management for a Construction Project. Sustainability 2023, 15, 12836.
Abstract
Big Data Technologies is one of the disruptive technologies that influence every business, including the construction industry. The Thai government is attempting to use machine learning technique from part of analytic by Big Data Technologies to forecast costs for public building projects. However, it was never developed, and They did not implement it with traditional data. In this study, traditional data is processed to predict the behavior of Thai government construction projects by using a machine learning model. Additionally, the data was collected from the government procurement system in 2019. There are eight input data including departmental groupings, project types, procurement methods, length, winning price over standard price, even criteria were examined, including winning price over budget and standard price above budget. Additionally, a range of classification techniques, including an artificial neural network (ANN), Decision tree (DC), K-nearest neighbor (KNN), were used in this study (ANN). According to the results, ANN has the greatest predicting accuracy with 78.9 percent after hyperparameter tuning. The study confirms that data from the Thai Government Procurement System can be usefully investigated using machine learning techniques from Big Data technologies.
Keywords
Artificial neural network; Procurement management; Construction budgeting; Machine learning
Subject
Engineering, Civil Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
