ML Driven Inventory Management System & Supply Chain Optimization: A Survey Paper

Sanket Pimprikar , Neha Kumar Patkulkar , Om Prakash Varma , Abhinav Arun Ughade , Dr. Vandana Rohokale

Inventory Optimization, Inventory Management System, Machine Learning, XGBoost, Random Forest, LSTM, Demand Forecasting, Supply chain management, Time Series Forecasting, Cost & Downtime Reduction, ensemble learning.

Precise Demand Forecasting of Components in the Manufacturing industry is critical to supply chain management, as various factors affect the demand for the product. To regulate and maintain the buffer stock of components in the Inventory is necessary. This project focuses on reducing the downtime in the manufacturing process by predicting the demand for components and providing analysis on the buffer stock to be maintained to avoid downtime and overspending of company resources to acquire the components, which have a volatile demand in the industry. The project focuses on inventory optimization, cost reduction & reducing downtime. This paper aims to present an integrated forecasting strategy for intermittent or volatile demand of components in the manufacturing industry by comparing the accuracy of various machine learning models like Random Forest, XGBoost, and LSTM. Enhancing supply chain strategies by providing invaluable insights into demand forecasting of the components is the aim of this machine learning model for informed decision-making.

Volume 10 Issue 1, January-2025

Pages : a229-a234