MANUFACTURING MANAGEMENT SYSTEM: LOGISTIC 1 (PROCUREMENT, VENDOR PORTAL, WAREHOUSE MANAGEMENT) WITH DEMAND FORECASTING AND DISCREPANCY DETECTION USING BRAIN.JS

Abstract

With the continuous advancement of digital technologies, the manufacturing sector is increasingly adopting intelligent systems to enhance logistics operations. However, many organizations still depend on manual processes for procurement, vendor communication, and warehouse management. These outdated methods often result in delays, data inconsistencies, and inaccurate demand forecasting, ultimately affecting productivity and increasing operational costs. To address these concerns, this study presents the Manufacturing Management System: Logistic 1—a unified logistics solution integrating Procurement, Vendor Portal, and Warehouse Management with demand forecasting and discrepancy detection capabilities using Brain.js. The system is designed to streamline logistical workflows, improve data accuracy, and support predictive decision-making for better supply chain performance. The system was developed using the Agile methodology, which divided the process into iterative sprints to ensure continuous feedback and alignment with operational requirements. Stakeholder interviews and real-time usability testing were conducted to validate functional effectiveness. Brain.js, a JavaScript-based neural network library, was utilized to implement demand forecasting and discrepancy detection modules. These AI features allow the system to analyze historical data and identify patterns, enabling adaptive and data-driven logistics management. The implementation of the system led to substantial improvements in logistics accuracy and efficiency. The use of Brain.js reduced forecasting errors and improved inventory tracking, which optimized warehouse processes such as receiving, storing, and stock monitoring. The vendor portal enhanced supplier coordination and minimized lead times. Additionally, the system’s secure architecture ensured reliability in managing sensitive operational data, making it suitable for deployment in critical manufacturing environments. This study demonstrates the potential of AI-enhanced logistics systems to transform traditional manufacturing practices. By minimizing manual errors, improving warehouse operations, and enabling predictive analytics, the system supports more informed decision-making. The Agile development approach allowed for flexibility and iterative enhancement based on user feedback. Overall, the Manufacturing Management System: Logistic 1 establishes a scalable, intelligent framework that can support future innovations in logistics and supply chain management.