Leveraging Deep Learning For Enhanced Transportation Management In Supply Chains

Abstract

The online shopping space has rapidly grown, and with it, a specific need for speedy and accurate shipping. To keep up, traditional supply chain practices and methods have needed to be re-examined. As a result, today's supply chains are generally employing more technology to better track every step of the process through to and from warehouse management. Warehousing, being the heart of the supply chain, the development of inventory management and space constraints within the warehouse deserves more attention. Since intelligence and efficiency are the most significant aspects of a warehouse, the preceding use of machine learning-based predictive analytics deals with the data collected earlier. In this study, advancements from machine learning to deep learning with functional objectives are the ultimate thing, which, if applied, will establish the benchmark performance of operational optimization in modern warehousing activities. Successfully integrating advanced technologies into the supply chain requires the proper merging of advanced analytical systems with variabilities of constraint optimization problems. This is one of the many dimensions that the traditional framework lacks. Making use of only advanced computational predictive analytics, behaviors are self-improved if and only if the actions of the warehousing network are frequently logged. In the development of further EDM towards big data, there exist numerous areas of research. Correct integration of predictive analytics with constraint optimization problems is one. Assessing the different impacts of big data on planning and design methodology in direct comparison to normal data is another. With the extensive involvement of deep learning techniques in modern warehousing operations, different studies considering a large amount of data come next. Incorporating each of these studies will solve many industrial issues.