| Title |
A data-driven decision-making approach for evaluating the projects according to resilience, circular economy and industry 4.0 dimension |
| ID_Doc |
16162 |
| Authors |
Nessari, S; Ghanavati-Nejad, M; Jolai, F; Bozorgi-Amiri, A; Rajabizadeh, S |
| Title |
A data-driven decision-making approach for evaluating the projects according to resilience, circular economy and industry 4.0 dimension |
| Year |
2024 |
| Published |
|
| DOI |
10.1016/j.engappai.2024.108608 |
| Abstract |
Multi-industry organizations constantly define new projects for development and progression. However, the noteworthy point is that there are many options for defining new projects and allocating resources to them, from which the best choices must be selected among the candidate projects. In today's world, due to extensive changes in business conditions, traditional performance metrics are not suitable for project evaluation, and projects that can enhance organizational resilience and serve communities in line with economic and environmental components should be selected. Moreover, considering the widespread changes in digital transformation over the past decade, paying attention to Industry 4.0 standards in project selection is important. In this context, the main goal of this study is to design a data-driven decision-making model based on machine learning for evaluating and selecting projects in line with resilience, circular economy, and Industry 4.0 criteria. In the first step, 21 indicators were identified, and their weights were determined using the fuzzy best-worst method (FBWM). Then, using the weighted fuzzy inference system method (WFIS), rules for labeling data were established, and finally, a model for predicting and evaluating project performance was defined using the Light Gradient Boosting Machine algorithm. The findings indicate that the indicators "Increase market share using Industry 4.0 technologies" and "Net present value" are the most important in project evaluation. The developed model accurately evaluates projects with more than 93% accuracy, performing better than other algorithms and demonstrating the high performance of data-driven algorithms in project evaluation. |
| Author Keywords |
Project selection; Data -driven decision making; Fuzzy best -worst -method; Fuzzy inference system; Light gradient boosting machine; Industry 4.0 |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED) |
| EID |
WOS:001247374500001 |
| WoS Category |
Automation & Control Systems; Computer Science, Artificial Intelligence; Engineering, Multidisciplinary; Engineering, Electrical & Electronic |
| Research Area |
Automation & Control Systems; Computer Science; Engineering |
| PDF |
|