The Implementation of Machine Learning in the Development of Sustainable Supply Chains

• Main Authors: Khan, Shakir, Sharma, Pooja, Prasad, K Raghav, D, Srinivas, Serajuddin, Mohammad, Ayub, Rashid
• Format: Conference Proceeding
• Language: English
• Subjects: Data analysis; Decision making; Education; Efficiency; Machine learning; Monitoring; Supply chain management; Supply chains; Support vector machines; Sustainability
• ISSN: 2687-7767
• DOI: 10.1109/UPCON59197.2023.10434528

Supply chain management is changing, as well as machine learning (ML) has become a vital tool in this process. This study explores the significance of machine learning (ML) in improving the sustainability and efficiency of supply chains. Organizations can keep track of vehicle status, expedite deliveries, optimize transportation, as well as foster sustainable growth by utilizing machine learning. Using machine learning (ML) has reduced costs, sped up decision-making, strengthened operational management, and allocated resources more effectively, all of which have increased long-term profitability. Conventional techniques for monitoring the movements of items have proven to be expensive and ineffective, requiring a large number of personnel. On the contrary, machine learning (ML) enables supply chain networks to anticipate and analyse abnormalities, so enabling prompt and well-informed decision-making. While traditional methods frequently fail to handle unstructured data from many sources, machine learning (ML) is a highly efficient way of analysing data, finding patterns, and producing results quickly. The goal of machine learning (ML) is to anticipate supply chain effectiveness, optimize resource consumption, cut costs, and promote growth through the application of a variety of algorithms. The importance of machine learning (ML) in supply chain management continues to increase as data volume increases. With an emphasis on the United Arab Emirates, the study uses a descriptive data-based methodology as well as draws from primary and secondary sources. In order to address vendor selection including strategic decision-making, the project investigates the incorporation of supervised learning, quality education (Q education), and support vector machines (SVM). The ultimate goal is to lower the expenses related to product mobility.