Abstract

The retail systems that are a mission-critical need a fine balance between the creative flexibility of Artificial Intelligence and the strict dependability of symbolic logic. In this paper, discussed the design and deployment of a Cloud-Native Hybrid AI-Rule Engine specifically exploring systems suitable to high-stakes retail settings, including in real-time inventory reconciliation and fraud detection. This research uses a simulation dataset that contains four hundred and seventy-six data items that are illustrations of different retail transactions, consumer behavior, and logistical anomalies. With the help of a cloud-native system, the system is horizontally scalable and has fault tolerance. The tools that were used in this study are Kubernetes as a container orchestrator, dedicated microservices as a model serving system, and a distributed rule management system as deterministic logic execution system. The findings suggest that the hybrid method considerably performs better, compared to the standalone AI models, regarding explainability and can be used to cut the false-positive rates of pure rule-based systems. This integration offers a powerful framework that assists the retailers in automating complex decisions making without compromising on the business policies.

References

• M. Stine, Migrating to Cloud-Native Application Architectures. O’Reilly Media, 2015.
• C. Pahl, A. Brogi, J. Soldani, and P. Jamshidi, “Cloud container technologies: A state-of-the-art review,” IEEE Trans. Cloud Comput., vol. 7, no. 3, pp. 677–692, 2019.
• F. Li, “Cloud-native database systems at Alibaba: Opportunities and challenges,” Proc. VLDB Endow., vol. 12, no. 12, pp. 2263–2272, 2019.
• S. Kumar and R. Goyal, “Modeling continuous security: A conceptual model for automated DevSecOps using open-source software over cloud (ADOC),” Comput. Secur., vol. 97, p. 101967, 2020.
• N. Kratzke and R. Siegfried, “Towards cloud-native simulations—Lessons learned from the front-line of cloud computing,” J. Def. Model. Simul., vol. 18, no. 1, pp. 39–58, 2021.
• J. Henning and W. Hasselbring, “A configurable method for benchmarking scalability of cloud-native applications,” Empir. Softw. Eng., vol. 27, no. 6, p. 143, 2022.
• J. Kosinska, B. Baliś, M. Konieczny, M. Malawski, and S. Zieliński, “Toward the observability of cloud-native applications: The overview of the state-of-the-art,” IEEE Access, vol. 11, pp. 73036–73052, 2023.
• J. Alonso et al., “Understanding the challenges and novel architectural models of multi-cloud native applications—A systematic literature review,” J. Cloud Comput., vol. 12, no. 1, p. 6, 2023.
• S. Deng et al., “Cloud-native computing: A survey from the perspective of services,” 2023.
• S. Nascimento et al., “Availability, scalability, and security in the migration from container-based to cloud-native applications,” Computers, vol. 13, no. 8, p. 192, 2024.
• P. Bellavista et al., “Exploiting microservices and serverless for Digital Twins in the cloud-to-edge continuum,” Future Gener. Comput. Syst., vol. 157, pp. 275–287, 2024.
• D. Alsadie, “Artificial intelligence techniques for securing fog computing environments: Trends, challenges, and future directions,” IEEE Access, vol. 12, pp. 151598–151648, 2024.
• H. Boye, “Strengthening cloud security through advanced encryption and anomaly detection techniques for secure data storage and transmission,” FMDB Trans. Sustain. Comput. Lett., vol. 2, no. 3, pp. 153–163, 2024