RetailIQ: An Integrated Cart Management and Business Analytics Platform for Small and Medium Retail

This paper presented RetailIQ, a retail management and ana-lytics platform that consolidates QR-based customer shopping, NLP-powered conversational assistance, multi-modal payment processing, retailer administration, and machine learning de-mand forecasting into a single cloud-native system. The plat-form targets the small and medium Indian retailer segment the numerically largest and most underserved portion of India’s retail market where no comparable affordable unified solution currently exists. The principal technical contributions include an HMAC-SHA256-secured QR product interaction model requiring no RFID hardware; a rule-based intent-classification NLP as-sistant with text and voice support; an atomic server-side inventory reservation mechanism preventing double booking; a Redis-backed idempotency engine eliminating duplicate orders under payment gateway retries; and a dual-model ML pipeline combining Prophet 30-day seasonal forecasting with Light-GBM 7-day velocity prediction, augmented by KL-divergence drift detection and automated retraining. Live prototype validation on real transaction data con-firmed correct end-to-end behaviour across all subsystems: HMAC integrity verification including rejection of tampered QR codes, cart management, payment settlement, idempotency deduplication, and accurate computation of all six analytics metrics including velocity surge alerting and AI-generated op-erational recommendations. The deployed system is accessible at https://retailiq-saas.vercel.app/. Future work will extend the platform with transformer-based NLP, multilingual support, multi-store management, and edge-deployed forecasting to serve a broader and more diverse retailer base across India.

[1]     J. Guo, J. Wang, and Y. Zhang, “Smart shopping cart system based on RFID and wireless sensor networks,” International Journal of Computer Applications, vol. 182, no. 42, pp. 1–5, 2019. [2]     Amazon, “Amazon Go: Just walk out technology,” https://www.amazon. com/b?node=16008589011, 2023. [3]     M. McTear, Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Synthesis Lectures on Human Language Tech-nologies, Morgan & Claypool, 2017. [4]     S. Chhabra and R. Agarwal, “Digital payments in India: A study of growth and adoption,” International Journal of Recent Technology and Engineering, vol. 8, no. 6, pp. 1224–1231, 2020. [5]     S. J. Taylor and B. Letham, “Forecasting at scale,” The American Statistician, vol. 72, no. 1, pp. 37–45, 2018. [6]     G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Liu, “LightGBM: A highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, pp. 3146–3154, 2017. [7]     R. Sharma, P. Verma, and A. Joshi, “Sales forecasting in retail using machine learning: A case study on Big Mart dataset,” International Journal of Scientific Research in Engineering and Management (IJSREM), vol. 8, no. 4, pp. 1–7,  2024.  [Online].  Available:  https://ijsrem.com/download/ sales-forecasting-in-retail-using-machine-learning-a-case-study-on-big-mart-dataset/ [8]     A. Ghosh, S. Das, and D. Mukherjee, “Consumer behavior analysis in retail using data mining techniques,” in Proceedings of the International Conference on Data Science and Analytics, pp. 112–119, 2021. [9]     A. Al-Momani, M. Hussain, and M. Ahmad, “A survey on security and trust in e-commerce systems,” Journal of Information Security and Applications, vol. 51, 2020. [10]    A. Ratner, C. De Sa, S. Wu, D. Selsam, and C. Re, “Data programming: Creating large training sets, quickly,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 29, pp. 3567–3575, 2016.