Premium
Analyzing the factors affecting environmental risks of projects using a hybrid approach of DEMATEL‐ANP, artificial neural network: A case study
Author(s) -
Ershadi Mohammad Javad,
Ashtiyani Fatemeh Karimi
Publication year - 2019
Publication title -
environmental quality management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.249
H-Index - 27
eISSN - 1520-6483
pISSN - 1088-1913
DOI - 10.1002/tqem.21647
Subject(s) - ranking (information retrieval) , risk analysis (engineering) , rank (graph theory) , risk management , analytic network process , process (computing) , computer science , quality (philosophy) , investment (military) , artificial neural network , analytic hierarchy process , project risk management , business , project management , operations research , engineering , project portfolio management , artificial intelligence , systems engineering , finance , philosophy , mathematics , epistemology , combinatorics , politics , law , political science , operating system
The increasing growth of the economy in each country necessitates a great amount of investment in infrastructure. The belief that projects involve various uncertainties, such as technical skills, management quality, and the like, indicates that most projects fail to achieve their aims, interests, costs, as well as their timeframes and space requirements. As the environment can pose significant uncertainty to any project, environmental risks should be deeply studied by project management departments. This study intends to analyze as a case the environmental risk management system within a consulting firm. From this analysis, each aspect of a project's environmental risk management is ranked using a fuzzy analytical network process (ANP), a neural network algorithm, and a decision‐making trial and evaluation laboratory (DEMATEL) methodology. From the organizational aspect, budget risk is the most significant. From the technical aspect, the risk of regulations is the most important one. Finally, the risk of project failure from poor communication is another identified main risk in this research. By studying high‐ranking items in this hierarchy, it can be understood that these criteria exist in different aspects; therefore, all aspects of the risk should be taken into account to cover and assess risk. A neural network algorithm for validating and reassessment of ranking is employed. Results of this application showed that, based on Spearman's rank correlation method, two different approaches resulted in similar rankings. Finally, some practical implications for responding to the most highly ranked risks are proposed.