SupplyVision AI: A Machine Learning-Driven Material Demand Forecasting System for Intelligent Supply Chain Management

Main Article Content

Mehul a Sagoti

Abstract

Modern supply chains are increasingly vulnerable to demand unpredictability, resulting in significant operational and financial inefficiencies. Traditional forecasting methods—reliant on manual estimation, simple statistical averages, and rigid rule-based systems—fail to adapt to the dynamic and complex nature of contemporary markets. This paper presents SupplyVision AI, a machine learning-driven material demand forecasting system designed to address the critical information, accuracy, and efficiency gaps inherent in conventional supply chain planning. The system employs Python-based machine learning models including Linear Regression and Random Forest Regressor, integrated within a Flask-powered web application, backed by a PostgreSQL relational database, and visualized through interactive Power BI dashboards. Performance evaluation was conducted using standard regression metrics including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² coefficient of determination. Functional and load testing validated the reliability and scalability of the deployed backend under realistic traffic conditions. The proposed framework demonstrates measurable improvements in forecasting accuracy, procurement planning efficiency, and overall supply chain responsiveness, offering a scalable, data-driven alternative to legacy forecasting paradigms

Article Details

Section

Articles

Author Biography

Mehul a Sagoti

Department of Computer Science and Engineering                                                                  Geetanjali Institute of Technical Studies                                                   

                            Udaipur, India                                                                                    

References

[1] T. J. Smoothey and R. K. Patel, "Machine Learning Applications in Supply Chain Demand Forecasting: A Systematic Review," IEEE Transactions on Engineering Management, vol. 69, no. 4, pp. 1423–1438, Aug. 2022.

[2] Y. Chen, H. Liu, and J. Zhang, "Random Forest-Based Demand Forecasting Model for Retail Supply Chains," in Proc. IEEE Int. Conf. Big Data and Smart Computing (BigComp), Busan, South Korea, 2021, pp. 234–241.

[3] A. K. Singh and P. Sharma, "Deep Learning vs. Traditional Machine Learning for Inventory Demand Prediction: A Comparative Analysis," International Journal of Production Economics, vol. 245, pp. 108–119, Mar. 2022.

[4] G. Palshikar and S. Athavale, "Demand Forecasting Using Machine Learning for E-Commerce Platforms," in Proc. IEEE Int. Conf. Advances in Computing, Communications and Informatics (ICACCI), Bangalore, India, 2018, pp. 1045–1050.

[5] F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.

[6] W. McKinney, "Data Structures for Statistical Computing in Python," in Proc. 9th Python in Science Conf. (SciPy), Austin, TX, USA, 2010, pp. 51–56.

[7] L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001.

[8] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed. New York, NY, USA: Springer, 2009.

[9] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann, 2011.

[10] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, Cambridge, MA, USA: MIT Press, 2016.