Prediction of multiproject resource conflict risk via an artificial neural network
Engineering, Construction and Architectural Management
ISSN: 0969-9988
Article publication date: 20 November 2020
Issue publication date: 4 November 2021
Abstract
Purpose
Inadequate balancing of resources often results in resource conflict in the multiproject management process. Past research has focused on how to allocate a small amount of resources optimally but has scarcely explored how to foresee multiproject resource conflict risk in advance. The purpose of this study is to address this knowledge gap by developing a model to predict multiproject resource conflict risk.
Design/methodology/approach
A fuzzy comprehensive evaluation method is used to transform subjective judgments into quantitative information, based on which an evaluation index system for multiproject resource conflict risk that focuses on the interdependence of multiple project resources is proposed. An artificial neural network (ANN) model combined with this system is proposed to predict the comprehensive risk score that can describe the severity of risk.
Findings
Accurately predicting multiproject resource conflict risks in advance can reduce the risk to the organization and increase the probability of achieving the project objectives. The ANN model developed in this paper by the authors can capture the essential components of the underlying nonlinear relevance and is capable of predicting risk appropriately.
Originality/value
The authors explored the prediction of the risks associated with multiproject resource conflicts, which is important for improving the success rate of projects but has received limited attention in the past. The authors established an evaluation index system for these risks considering the interdependence among project resources to describe the underlying factors that contribute to resource conflict risks. The authors proposed an effective model to forecast the risk of multiproject resource conflicts using an ANN. The model can effectively predict complex phenomena with complicated and highly nonlinear performance functions and solve problems with many random variables.
Keywords
Acknowledgements
The authors would like to acknowledge the assistance of SO JUMP in questionnaire survey, and are grateful to all the respondents in the questionnaire.Funding: This work was supported by the National Natural Science Foundation of China [No. 71802003], Ministry of Education Humanities and Social Sciences Fund [No. 17XJC630001], Soft Science Foundation of Shaanxi Province [No. 2017KRM123], Soft Science Foundation of Xi'an City [2019111813RKX002SF006–5].Data availability statement: Data generated or analyzed during the study are available from the corresponding author by request.Author contributions: All authors contributed equally to this work. All authors wrote, reviewed and commented on the manuscript. All authors have read and approved the final manuscript.Conflicts of interest: The authors declare no conflict of interest.
Citation
Bai, L., Wang, Z., Wang, H., Huang, N. and Shi, H. (2021), "Prediction of multiproject resource conflict risk via an artificial neural network", Engineering, Construction and Architectural Management, Vol. 28 No. 10, pp. 2857-2883. https://doi.org/10.1108/ECAM-03-2020-0201
Publisher
:Emerald Publishing Limited
Copyright © 2020, Emerald Publishing Limited