Designing AI-Powered Frontend Systems for Real Time Decision-Making in Large-Scale Retail and Supply Chain Platforms

References

[1] Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138–52160.

[2] Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett,

[3] P. N., Inkpen, K., & Teevan, J. (2019). Guidelines for human-AI interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (pp. 1–13). ACM.

[4] Benbasat, I., & Zmud, R. W. (1999). Empirical research in information systems: The practice of relevance. MIS Quarterly, 23(1), 3–16.

[5] Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley.

[6] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM.

[7] Chen, Y., Zhang, L., & Liu, W. (2021). Real-time supply chain optimization using edge computing and deep reinforcement learning. IEEE Transactions on Engineering Management, 68(4), 1125–1138.

[8] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

[9] IHL Group. (2024). Global inventory distortion report 2024. IHL Research.

[10] Ivanov, D. (2020). Predicting supply chain resilience through machine learning: A systematic review.

[11] International Journal of Production Research, 58(16), 4914–4936.

[12] Jennings, N. R., Sycara, K., & Wooldridge, M. (2001). A roadmap of agent research and development. Autonomous Agents and Multi-Agent Systems, 1(1), 7–38.

[13] Kumar, A., & Mangla, S. K. (2022). Forecasting methods for inventory optimization and dynamic pricing. Journal of Business Research, 144, 112–128.

[14] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (pp. 4765–4774). Curran Associates.

[15] Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2020). The M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting, 38(4), 1346–1364.

[16] Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1–38.

[17] Nikiforidis, K., Kyrtsoglou, A., Vafeiadis, T., et al. (2023). Explainable AI in Industry 4.0: A systematic review. ICT Express, 9(4), 645–655.

[18] Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39.

[19] Seyedan, M., & Mafakheri, F. (2023). Ensemble deep learning for demand forecasting and inventory optimization. Computers & Industrial Engineering, 175, 108–122.

[20] Student. (1908). The probable error of a mean. Biometrika, 6(1), 1–25.

[21] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2019). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 6(3), 637–646.

[22] Thejovathi, M., & Rao, M. V. P. C. S. (2024). Evaluation of AI-driven autonomous and TinyML applications for enterprise systems. IEEE Conference Proceedings.

[23] Wooldridge, M. (2009). An Introduction to MultiAgent Systems (2nd ed.). Wiley.

@article{1722383,
      author = {Sohail Sayed},
      title = {Designing AI-Powered Frontend Systems for Real Time Decision-Making in Large-Scale Retail and Supply Chain Platforms},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {8},
      number = {1},
      pages = {949-961},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722383.pdf},
      abstract = {The large-scale retail and supply chain systems have overwhelmed the front end decision support tools capabilities, causing delays in response and inefficiencies in inventory allocation, pricing and customer experience. Although the research that has been conducted so far has mostly concentrated on the optimization of the backends and predictive analytics, little has been done on actually integrating real-time and AI-based decision intelligence into frontend systems. The paper will present a proposal of an AI-powered frontend system (AIFS), which is a hybrid demand forecasting model, a multi agency coordination, and an explainable AI module on a real time streaming architecture. It is implemented as a modular system that comprises of user interaction layer, real time inference engine, continuous feedback loop to provide adaptive learning and interactive visualization layer. In order to test the proposed method, we create the simulation-based experimental setup based on the use of the M5 retail data that is supplemented with the synthetic streaming and IoT data to simulate real-time working conditions. It was experimentally shown that the suggested system is capable of cutting down the decision latency by up to 62 percent and enhancing inventory turnover by 18 percent in contrast to baseline rule-based systems in simulated real-time environments. The findings indicate that frontend-native AI systems are potentially useful in improving real-time operational decision-making processes and form the basis of future studies on human-AI collaborative interfaces in the retail and supply chain management.},
      keywords = {ai-powered frontend, real-time decision-making, retail supply chain, edge ai, explainable ai, demand forecasting, multi-agent systems},
      month = {July},
      doi = {https://doi.org/10.64388/IREV8I1-1722383}
  }