Optimizing Regional Business Performance: Leveraging Business and Data Analytics in Logistics & Supply Chain Management for USA's Sustainable Growth

Abstract

The logistics and supply chain management (SCM) sector plays a paramount role in the economic development and growth of countries. In the USA, the effectiveness and efficiency of logistics and SCM functions directly influence regional organizational performance and long-term economic sustainability. The prime objective of this research is to explore the phenomenon of optimizing regional business performance through the application of data and business analytics in logistics and supply chain management for the sustainable growth of the US economy. In this study, the researcher employed machine learning methodologies, specifically ANN, RNN, and SVM, to forecast lead times for purchasing aluminum products. In the research, historical data was collected from the database of one of the aluminum-producing companies in the USA for the last 10 years. In particular, a sample of 38,500 orders of aluminum profiles was adopted for the current study. Retrospectively, the Recurrent Neural Network and the Support Vector Machine displayed the most favorable outcomes in predicting lead time in the supply chain. Particularly, RNN had the least Mean Average Error (MAE) on the testing set (447.72), followed by SVM (453.04), MLR (453.22), and NN (455.41). By deploying these algorithms, the government can optimize inventory degrees, minimize stockouts, and reduce excess inventory. This results in enhanced efficiency, diminished carrying costs, and elevated consumer satisfaction, leading to cost savings and heightened profitability for government companies within the supply chain.