Retail IQ AI Management System: Implementation, Design Analysis, and Performance Evaluation

This paper presented the detailed implementation and design analysis of the Retail IQ AI Management System across all phases of the SDLC. The system was implemented using a Java Spring Boot RESTful backend, HTML/CSS/JavaScript frontend, MySQL relational database, and a Java-native item- based collaborative filtering recommendation engine. Fifteen functional test cases achieved 100% pass rates. Performance testing under 50 concurrent users confirmed average API response times below 130 ms and page load times below 1.4 seconds. Key design decisions—stateless JWT authentication, pre-computed affinity cache, and lazy-fetch JPA relationships—were analytically validated through empirical measurements presented in Section 6. The system demonstrates that a focused, domain-specific implementation can deliver robust retail intelligence capabilities at a fraction of the cost and complexity of generic e-commerce platforms. Future implementation directions include: (i) Razorpay or Stripe payment gateway integration for complete digital transaction support; (ii) React Native mobile application development for Android and iOS, consuming the existing Spring Boot API without backend modification; (iii) replacement of the batch affinity matrix refresh with an event- driven Kafka consumer that updates recommendation scores in real-time on each order placement event; (iv) LSTM-based demand forecasting trained on historical order items time- series data to replace the simple rolling-average days-to- stockout estimate; (v) customer product rating and review module  with  VADER  sentiment  analysis  for  quality monitoring; and (vi) Docker containerisation with Kubernetes orchestration to support horizontal scaling beyond the current single-server embedded Tomcat deployment.

[1]  E. Turban, J. Outland, D. King, J. K. Lee, T. P. Liang, and D. C. Turban, Electronic Commerce 2018: A Managerial and Social Networks Perspective, 9th ed. Cham, Switzerland: Springer, 2018. [2]  K. C. Laudon and C. G. Traver, E-Commerce 2023: Business, Technology, and Society, 18th ed. Hoboken, NJ: Pearson Education, 2023. [3]   R. S. Pressman and B. R. Maxim, Software Engineering: A Practitioner's Approach, 9th ed. New York, NY: McGraw-Hill Education, 2019. [4]    G. Linden, B. Smith, and J. York, "Amazon.com Recommendations: Item-to-Item Collaborative Filtering," IEEE Internet Computing, vol. 7, no. 1, pp. 76-80, Jan./Feb. 2003. [5]  C. Walls, Spring Boot in Action. Shelter Island, NY: Manning Publications, 2016. [6]   I. Sommerville, Software Engineering, 10th ed. Harlow, UK: Pearson Education, 2015. [7]  C. C. Aggarwal, Recommender Systems: The Textbook. Cham, Switzerland: Springer, 2016. [8]   H. Garcia-Molina, J. D. Ullman, and J. Widom, Database Systems: The Complete Book, 2nd ed. Upper Saddle River, NJ: Pearson Prentice Hall, 2009. [9]   M. Fowler, Patterns of Enterprise Application Architecture. Boston, MA: Addison-Wesley, 2002.                MySQL AB, "MySQL 8.0 Reference Manual," [Online].