AI-based Procurement System: Optimization of Material Ordering and Inventory Management in Volatile Markets

Accurate forecasting of material prices is essential for companies to navigate market volatility and maintain profitability. This study addresses the challenges companies face in planning and procurement due to volatile material prices and geopolitical events by developing an AI-based model to optimize raw material purchase decisions. Three AI models, Convolutional Neural Network (CNN), Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM), were developed and analyzed using historical material price data. The LSTM model was found to be the most effective in forecasting future material prices. An algorithm was created to determine the optimal order time and quantities based on AI-generated forecasts. Comparing the LSTM-based procurement strategy with a normal ordering system revealed 4 % cost savings between November 2022 and October 2024. The results demonstrate the potential of AI-based models to improve procurement Efficiency and cost-effectiveness in the face of market volatility.