Machine Learning‐Driven Demand Forecasting in the Automotive Supply Chain

Demand forecasting is a critical component and a major challenge within supply chain management. Accurate forecasts can help reduce costs, improve operational efficiency, and increase overall company performance. In the automotive industry, where demand can change quickly, having reliable forecasting methods is essential for meeting customer needs and avoiding disruptions. The main purpose of this study is to identify the best forecasting technique to generate accurate customer demand predictions in the automotive supply chain. Real historical data from an automotive company covering the years 2020–2025 was used to train and test different forecasting models. The accuracy of each model was evaluated using four common metrics: root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and symmetric mean absolute percentage error (SMAPE). The results show that the long short‐term memory (LSTM) model provides better forecasting accuracy compared to other methods. This suggests that using deep learning models like LSTM can help companies improve their supply chain performance by making better demand predictions. In addition, our study can support supply planners in applying machine learning techniques to improve forecasting across different data sources.