An application of hybrid models combining regression tree and artificial neural network for demand forecasting: a case study of ceramic products

This case study aims to provide highly accurate demand forecasting by focusing on the most influential products. The models used include both Traditional Methods such as Weighted Moving Average (WMA), Double Exponential Smoothing (DES), Double Moving Average (DMA), and Simple Linear Regression (SLR) and Machine Learning methods, including Regression Tree, Artificial Neural Network (ANN), and a Hybrid Models combining Regression Tree and ANN with a Weighted Average Based on Error. The performance of each method will be evaluated using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) to determine the best approach. This study will benefit ceramic manufacturing by developing and evaluating accurate demand forecasting models.