University of Hertfordshire Research Archive

        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UHRABy Issue DateAuthorsTitlesThis CollectionBy Issue DateAuthorsTitles

        Arkivum Files

        My Downloads
        View Item 
        • UHRA Home
        • University of Hertfordshire
        • Research publications
        • View Item
        • UHRA Home
        • University of Hertfordshire
        • Research publications
        • View Item

        A Big Data Analytics Approach for Construction Firms Failure Prediction Models

        View/Open
        A_Big_Data_Analytics_Approach_for_Construction_Firms_Failure_Prediction_Models_1.pdf (PDF, 1Mb)
        Author
        Alaka, Hafiz
        Oyedele, Lukumon O.
        Owolabi, Hakeem O
        Akinade, Olugbenga O.
        Bilal, Muhammad
        Ajayi, Saheed O.
        Attention
        2299/21955
        Abstract
        Using 693 000 datacells from 33 000 sample construction firms that operated or failed between 2008 and 2017, failure prediction models were developed using artificial neural network (ANN), support vector machine, multiple discriminant analysis (MDA), and logistic regression (LR). The accuracy of the models on test data surprisingly showed ANN to have only a slightly better accuracy than LR and MDA. The ANN's number of units in the hidden layer and weight decay hyperparameters were consequently tuned using the grid search. Tuning process led to tedious machine computation that was aborted after many hours without completion. The state of art big data analytics (BDA) technology was, for the first time in failure prediction, consequently employed and the tuning was completed in some seconds. Mean accuracy from cross validation was used for selection of the model with best parameter values, which were used to develop a new ANN model that outperformed all previously developed models on test data. Subsequent use of selected variables to develop new models led to reduced tuning computational cost, but not improved performance. Since the real-life effect of a misclassification cost is greater than the tedious computation cost, it was concluded that BDA is the best compromise.
        Publication date
        2019-11-01
        Published in
        IEEE Transactions on Engineering Management
        Published version
        https://doi.org/10.1109/TEM.2018.2856376
        Other links
        http://hdl.handle.net/2299/21955
        Metadata
        Show full item record
        Keep in touch

        © 2019 University of Hertfordshire

        I want to...

        • Apply for a course
        • Download a Prospectus
        • Find a job at the University
        • Make a complaint
        • Contact the Press Office

        Go to...

        • Accommodation booking
        • Your student record
        • Bayfordbury
        • KASPAR
        • UH Arts

        The small print

        • Terms of use
        • Privacy and cookies
        • Criminal Finances Act 2017
        • Modern Slavery Act 2015
        • Sitemap

        Find/Contact us

        • T: +44 (0)1707 284000
        • E: ask@herts.ac.uk
        • Where to find us
        • Parking
        • hr
        • qaa
        • stonewall
        • AMBA
        • ECU Race Charter
        • disability confident
        • AthenaSwan