Smart Supply Chain Management using Big Data Analysis and Machine Learning

Supply chain management (SCM) is concerned with the movement of products, services, and information from points of origin to consumers via a network of interconnected organizations and activities. It is believed that capacity, demand, and cost are well-known variables in typical SCM challenges. In practice, however, there are uncertainties brought on by changes in client demand, supply chain management, organizational risks, and lead times. Demand uncertainty in particular has a significant impact on SC performance with wide-ranging implications for scheduling production, planning inventories, and organizing transportation. In this regard, demand forecasting is a crucial strategy for tackling supply chain uncertainty. Forecasting supply chain demand using big data analytics has been published in the supervised and unsupervised learning categories. In supervised learning, the inputs and outputs are known because the data are tagged with labels. Given a fresh unlabeled dataset, the supervised learning algorithms attempt to map the inputs to matching outputs by identifying the underlying connections between the inputs and outputs. The main motive for the authors is to prove that supply chain can be managed through machine learning and to get a novel accuracy along with comparison of the machine learning models.