Article Preview
Top1. Introduction
With the rapid development of the digital economy, the landscape of supply chain management (SCM) is undergoing profound transformations(Min et al., 2019). SCM plays a pivotal role in modern business operations by orchestrating the flow of goods and services from raw material suppliers to end consumers(Ben-Daya et al., 2019). It involves the coordination of various entities, including suppliers, manufacturers, distributors, retailers, and logistics providers, to ensure efficient production, distribution, and delivery of products(Lü & Hou, 2024; Pournader et al., 2021). In the era of the digital economy(Helo & Hao, 2022), SCM faces unprecedented challenges and opportunities driven by advancements in technology and changing consumer preferences(Fei et al., 2024).
The digital economy has transformed traditional supply chain paradigms(Del Giudice et al., 2021), ushering in an era of interconnectedness and data-driven decision-making. In this context, digital technologies such as big data analytics, artificial intelligence (AI)(J. Wang et al., 2024), and the Internet of Things (IoT) have revolutionized SCM practices, enabling real-time visibility, predictive analytics, and agile responsiveness to market fluctuations(Dai & Hansen, 2020; Li et al., 2020). Among these technologies, deep learning has emerged as a powerful tool for extracting insights from vast and complex supply chain data(Ni et al., 2020; Ning et al., 2024), empowering organizations to optimize their operations and enhance competitiveness.
However, despite the promising potential of these approaches, current methods face several significant challenges(Sharma et al., 2020). These include difficulties in integrating heterogeneous data sources, limitations in model interpretability(Ning et al., 2024), and the computational demands associated with training deep learning models on large-scale supply chain data(Baryannis et al., 2019). Furthermore, existing methods often lack the flexibility required to adapt to rapidly changing market dynamics, leading to suboptimal decision-making in dynamic supply chain environments(X. Wang et al., 2024). These limitations highlight the need for innovative approaches that can effectively address these challenges and enhance the overall performance and applicability of deep learning models in SCM(Nguyen et al., 2021; Pan et al., 2023).
Currently, researchers and practitioners are increasingly leveraging deep learning techniques to address various challenges and opportunities in SCM(Nagaiah, 2022; Ran et al., 2024). By harnessing the capabilities of deep neural networks, researchers aim to improve demand forecasting accuracy(Jalil et al., 2019), optimize inventory management, enhance transportation efficiency, and mitigate supply chain risks(Soori et al., 2023; Zhang & Shankar, 2023). Furthermore, deep learning enables the automation of decision-making processes and the development of adaptive supply chain systems capable of learning from past experiences and evolving market dynamics(Essien & Giannetti, 2020).