RetailEase: Design and Development of an AI-Integrated Multi-Store Retail Management System

This paper presented RetailEase, a comprehensive AI-integrated retail management system built on modern web technologies. The system successfully addresses the core challenges of multi-store inventory management, real-time communication, and intelligent decision support through LLM integration. Key contributions include: (1) a modular, scalable full-stack architecture combining Node.js, React, and React Native; (2) an AI chatbot with multi-provider LLM fallback for reliable natural language inventory queries; (3) rolebased access control ensuring appropriate data visibility across five user roles; (4) real-time WebSocket communication for live inventory updates and customer support; and (5) cross-platform accessibility through web and mobile applications from a single backend. Future work will focus on integrating computer vision for barcode scanning, implementing time-series forecasting models for demand prediction, and adding multi-language support for broader retail market adoption.

[1] Chopra, S., & Meindl, P. (2016). Supply Chain Management: Strategy, Planning, and Operation (6th ed.). Pearson. [2] Slack, N., Brandon-Jones, A., & Johnston, R. (2019). Operations Management (9th ed.). Pearson. [3] Fildes, R., Ma, S., & Kolassa, S. (2022). Retail forecasting: Research and practice. International Journal of Forecasting, 38(4), 1283–1318. [4] Brown, T., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. [5] Lubbers, P., Albers, B., & Salim, F. (2011). Pro HTML5 Programming. Apress. [6] Eisenman, B. (2016). Learning React Native. O'Reilly Media. [7] Fowler, M. (2018). Refactoring: Improving the Design of Existing Code (2nd ed.). Addison-Wesley. [8] Newman, S. (2021). Building Microservices (2nd ed.). O'Reilly Media.