期刊
JOURNAL OF BUSINESS RESEARCH
卷 154, 期 -, 页码 -出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.jbusres.2022.113357
关键词
Sustainable healthcare supply chain; Forecasting; Performance measurement; Deep learning; Network data envelopment analysis (NDEA)
类别
The study proposes a network data envelopment analysis (NDEA) model and a deep learning approach for predicting the sustainability of healthcare supply chains (HSCs). Technological advances such as deep learning, artificial intelligence (AI), and Blockchain have gained importance in HSCs and are seen as competitive advantages. The use of advanced performance evaluation techniques, including DEA, has garnered considerable attention in enhancing HSCs' performance. The results highlight the top-ranking HSCs that utilize fewer facilities, have desirable outputs, and minimal undesirable outputs.
The main objective of this study is to propose a network data envelopment analysis (NDEA) model and a deep learning approach for forecasting the sustainability of healthcare supply chains (HSCs). Technological advances manifested in approaches such as deep learning, artificial intelligence (AI), and Blockchain are of substantial importance throughout HSCs and are understood as competitive advantages. Furthermore, applying advanced performance evaluation techniques, including DEA in HSCs for enhancing performance has attracted momentous attention over the last two decades. To make use of these approaches, a network DEA (NDEA) model and a deep learning approach are developed to predict the sustainability of HSCs. The developed model in this paper can determine the optimal value of bounded connections. Using the DEA capabilities, the threshold of each of these bounded connections is obtained to maximize the efficiency of decision making units (DMUs). It also identifies the role of the dual-role connections for each DMU. The results show that HSCs that use the least facilities and have the most desirable output, as well as the least undesirable output, are in the top ranks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据