This study examines theoretical frameworks, methods, and key discoveries' practical, social, and theoretical impacts. Study envisions AI/ML SCM. Supply chain AI/ML is assessed by model optimisation, predictive analytics, and decision-making frameworks. Systematic literature reviews gather pertinent research. The authors read academic, conference, and industrial papers to learn. To uncover trends and insights, studies are critically assessed, classified, and synthesised. This study examines AI/ML supply chain demand forecasting, inventory management, logistics optimisation, and risk management. The research suggests deep learning, neural networks, evolutionary algorithms, and SVMs for supply chain issues. The review highlights SCM AI/ML implementation issues and AI/ML supply chain management pros and drawbacks. Researchers, practitioners, and policymakers may discover how AI and ML improve supply chain efficiency, cost, and networks.
TopIntroduction
In recent years, there has been a substantial paradigm shift in the industry of supply chain management (also known as SCM) (Chen, Y. et al., 2019), which may be attributed to the emergence of technologies that make use of artificial intelligence (AI) (Chen, P. Y., & Wang, F. K., 2020) and machine learning (ML). Because of this change, there have been considerable increases in both efficiency and efficacy. This shift in perspective was brought about as a direct result of the convergence of these various technological aspects. The ability of artificial intelligence and machine learning algorithms to analyse vast volumes of data (Dey, A., & Nair, A., 2019) and provide insights that can be put into action has resulted in a fundamental change to the conventional techniques of supply chain management. This change has been brought about as a direct result of the capabilities of these two types of algorithms. The proliferation of connected devices and appliances, often known as the Internet of Things (IoT) (Pandey, J. K. et al., 2022), is directly responsible for bringing about this shift. Bdataecause of this, businesses have been able to boost not just their operational efficiency (Gong, Y. et al., 2020) but also their methods of decision-making and their general efficacy.
The purpose of this article is to attempt to provide a comprehensive study of the several ways in which these technologies are utilised by focusing on the various applications of artificial intelligence (Ghaffari, A., & Rabbani, M., 2019) and machine learning (Kumar, A. et al., 2022) in supply chain management. Specifically, the article will examine the various ways in which these technologies can be used to manage supply chains. The potential benefits and the potential drawbacks that are linked with the utilisation of these technologies (Gunasekaran, A., & Ngai, E. W. T., 2017) are going to be the primary focal points of the inquiry that will be carried out.
The level of success that a company achieves is inversely proportional to a variety of factors, one of the most important of which is the way in which the company manages the supply chain that it employs (Christopher, M., 2016)). This management encompasses the entirety of the process of controlling the flow of goods and services, beginning with the procurement of raw materials and concluding with the distribution of finished items to end users.
This management starts with controlling the flow of commodities and services into and out of the organisation. It begins with the goal of obtaining the highest possible levels of both efficiency and effectiveness throughout the entire operation in every facet of it (Fawcett, S. E. et al., 2014). Companies may find it difficult to effectively manage their operations and adjust to the ever-evolving expectations of their consumers due to the fluidity and complexity of modern supply chains. This can make it difficult for companies to compete in today's global economy. As a result of this, it can be difficult for enterprises to compete in the modern economy on a global scale. In this scenario, artificial intelligence (AI) (Pandey, D. et al., 2021) and machine learning (ML) can be used because they provide cutting-edge capabilities that have the potential to revolutionise traditional supply chain techniques and provide a competitive advantage. These capabilities have the potential to revolutionise traditional supply chain approaches and provide a competitive advantage. These capabilities can be employed because AI (Pandey, B. K. et al., 2021c) and ML give cutting-edge capabilities that have the potential to disrupt traditional supply chain procedures (De Sousa Jabbour et al., 2018). As a result, these capabilities can be utilised. These qualities give AI and ML (Anand, R. et al., 2023) with cutting-edge capabilities that have the potential to transform the conventional ways of supply chain management. These capabilities have the potential to change the conventional ways of supply chain management.