A framework for big data analytics approach to failure prediction of construction firms

Alaka, Hafiz A.; Oyedele, Lukumon O.; Owolabi, Hakeem A.; Bilal, Muhammad; Ajayi, Saheed O.; Akinade, Olugbenga O.

Abstract

This study explored use of big data analytics (BDA) to analyse data of a large number of construction firms to develop a construction business failure prediction model (CB-FPM). Careful analysis of literature revealed financial ratios as the best form of variable for this problem. Because of MapReduce’s unsuitability for iteration problems involved in developing CB-FPMs, various BDA initiatives for iteration problems were identified. A BDA framework for developing CB-FPM was proposed. It was validated by using 150,000 datacells of 30,000 construction firms, artificial neural network, Amazon Elastic Compute Cloud, Apache Spark and the R software. The BDA CB-FPM was developed in eight seconds while the same process without BDA was aborted after nine hours without success. This shows the issue of not wanting to use large dataset to develop CB-FPM due to tedious duration is resolvable by applying BDA technique. The BDA CB-FPM largely outperformed an ordinary CB-FPM developed with a dataset of 200 construction firms, proving that use of larger sample size with the aid of BDA, leads to better performing CB-FPMs. The high financial and social cost associated with misclassifications (i.e. model error) thus makes adoption of BDA CB-FPMs very important for, among others, financiers, clients and policy makers.

Citation

Alaka, H. A., Oyedele, L. O., Owolabi, H. A., Bilal, M., Ajayi, S. O., & Akinade, O. O. (2020). A framework for big data analytics approach to failure prediction of construction firms. Applied Computing and Informatics, 16(1/2), 207-222. https://doi.org/10.1016/j.aci.2018.04.003

• Journal Article Type: Article
• Acceptance Date: Apr 11, 2018
• Online Publication Date: Mar 12, 2018
• Publication Date: Dec 31, 2020
• Deposit Date: Apr 19, 2018
• Publicly Available Date: Apr 19, 2018
• Journal: Applied Computing and Informatics
• Print ISSN: 2210-8327
• Electronic ISSN: 2210-8327
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 16
• Issue: 1/2
• Pages: 207-222
• DOI: https://doi.org/10.1016/j.aci.2018.04.003
• Keywords: big data analytics, failure prediction models, construction businesses, machine learning, MapReduce/Spark
• Public URL: https://uwe-repository.worktribe.com/output/869571
• Publisher URL: http://dx.doi.org/10.1016/j.aci.2018.04.003