University of Hertfordshire

From the same journal

By the same authors

Predicting Completion Risk in PPP Projects using Big Data Analytics

Research output: Contribution to journalArticlepeer-review

Standard

Predicting Completion Risk in PPP Projects using Big Data Analytics. / Owolabi, Hakeem O; Bilal, Muhammad; Oyedele, Lukumon O.; Alaka, Hafiz; Ajayi, Saheed O.; Akinade, Olugbenga O.

In: IEEE Transactions on Engineering Management, Vol. 67, No. 2, 21.11.2018, p. 430 - 453.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Owolabi, Hakeem O ; Bilal, Muhammad ; Oyedele, Lukumon O. ; Alaka, Hafiz ; Ajayi, Saheed O. ; Akinade, Olugbenga O. / Predicting Completion Risk in PPP Projects using Big Data Analytics. In: IEEE Transactions on Engineering Management. 2018 ; Vol. 67, No. 2. pp. 430 - 453.

Bibtex

@article{a7079e4d536341eba09655a67cdacdc2,
title = "Predicting Completion Risk in PPP Projects using Big Data Analytics",
abstract = "Accurate prediction of potential delays in PPP projects could provide valuable information relevant for planning, and mitigating completion risk in future PPP projects. However, existing techniques for evaluating completion risk remain incapable of identifying hidden patterns in risk behaviour within large samples of projects, which are increasingly relevant for accurate prediction. To effectively tackle this problem in PPP projects, this study proposes a Big Data Analytics (BDA) predictive modelling technique for completion risk prediction. With data from 4294 PPP project samples delivered across Europe between 1992 and 2015, a series of predictive models have been devised and evaluated using linear regression, regression trees, random forest, support vector machine and deep neural network for completion risk prediction. Results and findings from this study reveal that random forest is an effective technique for predicting delays in PPP projects, with lower average test predicting error than other legacy regression techniques. Research issues relating to model selection, training and validation are also presented in the study.",
keywords = "Benchmark, Completion risk (CR), Forecasting, Predictive modeling, Public private partnerships (PPP), Big Data;",
author = "Owolabi, {Hakeem O} and Muhammad Bilal and Oyedele, {Lukumon O.} and Hafiz Alaka and Ajayi, {Saheed O.} and Akinade, {Olugbenga O.}",
note = "{\textcopyright} 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission",
year = "2018",
month = nov,
day = "21",
doi = "10.1109/TEM.2018.2876321",
language = "English",
volume = "67",
pages = "430 -- 453",
journal = "IEEE Transactions on Engineering Management",
issn = "0018-9391",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

RIS

TY - JOUR

T1 - Predicting Completion Risk in PPP Projects using Big Data Analytics

AU - Owolabi, Hakeem O

AU - Bilal, Muhammad

AU - Oyedele, Lukumon O.

AU - Alaka, Hafiz

AU - Ajayi, Saheed O.

AU - Akinade, Olugbenga O.

N1 - © 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission

PY - 2018/11/21

Y1 - 2018/11/21

N2 - Accurate prediction of potential delays in PPP projects could provide valuable information relevant for planning, and mitigating completion risk in future PPP projects. However, existing techniques for evaluating completion risk remain incapable of identifying hidden patterns in risk behaviour within large samples of projects, which are increasingly relevant for accurate prediction. To effectively tackle this problem in PPP projects, this study proposes a Big Data Analytics (BDA) predictive modelling technique for completion risk prediction. With data from 4294 PPP project samples delivered across Europe between 1992 and 2015, a series of predictive models have been devised and evaluated using linear regression, regression trees, random forest, support vector machine and deep neural network for completion risk prediction. Results and findings from this study reveal that random forest is an effective technique for predicting delays in PPP projects, with lower average test predicting error than other legacy regression techniques. Research issues relating to model selection, training and validation are also presented in the study.

AB - Accurate prediction of potential delays in PPP projects could provide valuable information relevant for planning, and mitigating completion risk in future PPP projects. However, existing techniques for evaluating completion risk remain incapable of identifying hidden patterns in risk behaviour within large samples of projects, which are increasingly relevant for accurate prediction. To effectively tackle this problem in PPP projects, this study proposes a Big Data Analytics (BDA) predictive modelling technique for completion risk prediction. With data from 4294 PPP project samples delivered across Europe between 1992 and 2015, a series of predictive models have been devised and evaluated using linear regression, regression trees, random forest, support vector machine and deep neural network for completion risk prediction. Results and findings from this study reveal that random forest is an effective technique for predicting delays in PPP projects, with lower average test predicting error than other legacy regression techniques. Research issues relating to model selection, training and validation are also presented in the study.

KW - Benchmark

KW - Completion risk (CR)

KW - Forecasting

KW - Predictive modeling

KW - Public private partnerships (PPP)

KW - Big Data;

U2 - 10.1109/TEM.2018.2876321

DO - 10.1109/TEM.2018.2876321

M3 - Article

VL - 67

SP - 430

EP - 453

JO - IEEE Transactions on Engineering Management

JF - IEEE Transactions on Engineering Management

SN - 0018-9391

IS - 2

ER -