AI-Driven Demand Forecasting and Inventory Optimization Using Prophet-Based Time Series Modelling
Keywords:
Demand Forecasting,, Inventory Optimization, Prophet Model, Time Series Forecasting, FastAPI, Retail Analytics, Machine LearningAbstract
The increasing complexity of retail operations has intensified the need for precise demand estimation and efficient inventory management. This study proposes an integrated framework that combines time-series forecasting with automated inventory decision support to enhance supply chain performance. A forecasting model based on Prophet is employed to analyse historical sales data and generate future demand predictions, while a FastAPI-based backend facilitates real-time interaction with the system. To simulate practical retail conditions, multiple product categories with varying demand patterns and promotional influences are incorporated. An intelligent decision module evaluates predicted demand against available stock levels and classifies inventory status to identify potential shortages or stable conditions. The model’s performance is assessed by using standard metrics such as MAE, RMSE, and MAPE. Experimental evaluation demonstrates strong predictive performance, achieving an MAE of 5, RMSE of 5.39, and MAPE of approximately 3.55%, indicating high forecasting accuracy. The proposed approach offers a scalable and data-driven solution for improving operational efficiency in retail supply chains.
Downloads
References
[1] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed., OTexts, 2021.
[2] S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “Statistical and Machine Learning forecasting methods: Concerns and ways forward,” PLOS ONE, vol. 13, no. 3, 2018.
[3] G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis: Forecasting and Control, 5th ed., Wiley, 2015.
[4] S. J. Taylor and B. Letham, “Forecasting at scale,” The American Statistician, vol. 72, no. 1, pp. 37–45, 2018.
[5] H. Drucker et al., “Support Vector Regression Machines,” Advances in Neural Information Processing Systems, 1997.
[6] F. Chollet, Deep Learning with Python, Manning Publications, 2017.
[7] K. Greff et al., “LSTM: A Search Space Odyssey,” IEEE Transactions on Neural Networks, 2017.
[8] A. Jain, M. N. Murty, and P. J. Flynn, “Data clustering: A review,” ACM Computing Surveys, 1999.
[9] B. Praveenk et al., “Inventory Management using Machine Learning,” International Journal of Innovation in Science and Technology, 2020.
[10] K. F. Googerdchi et al., “Sales Forecasting in Retail Using Random Forest Regression: A Case Study on Walmart,” 2025 4th International Conference on Computing and Information, 2025.
[11] P. Verma, “Transforming supply chains through AI: demand forecasting, inventory management, and dynamic optimization,” Integrated Journal of Science and Technology, 2024.
[12] N. Mehdiyev et al., “Evaluating Forecasting Methods by Considering Different Accuracy Measures,” Procedia Comp. Sci., vol. 95, pp. 264–271, 2016.
[13] R. Kolge et al., “Ergonomic Design and Analysis of Workstations in Manufacturing Industries for Enhanced Safety and Productivity,” IRJIST, Vol. 1 Issue 1, pp. 01-09, 2026.
[14] A. Kadu et al., “Thermoelectric Generator for Waste Heat Recovery System,” IRJIST, Vol. 1 Issue 1, pp. 52-58, 2026.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dr. Sanjay B. Patil, Mitali Patil, Kshitija S. Thakur, Rasika Pimple, Shweta Patil (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the International Research Journal of Innovation in Science and Technology (IRJIST) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors retain the copyright of their work and grant the journal the right of first publication. Proper attribution to the authors and the journal is required for any reuse of the published content.
