When developing a production plan, accurate forecasting short-term demand is challenging for managers because a short forecast period indicates that the change in product demand exhibits an unsteady trend. Therefore, forecast models generated using a large amount of historical observations do not fully explain the data collected on developing patterns and, consequently, do not robustly forecast outcomes. However, if a low number of samples featuring the most recent information is used for developing a forecast, management efficiency could be enhanced and enterprises could gain a competitive advantage. To solve the problems associated with forecasting short-term demand when small datasets are available, we developed a residual discrete grey model that is based on modeling residual analysis. Specifically, we first applied the discrete grey model to create a forecasting model, and then used the obtained fitting residuals to generate training samples using the Latent Information function to learn the topology of a backpropagation neural network. Finally, the predictive errors obtained using the constructed network for adjusting the forecast to enhance the forecasting performance. We conducted an experiment using the demand data obtained from a thin film transistor liquid crystal display panel, and the results indicated that a highly accurate forecast could be obtained using the proposed modeling procedure. This finding suggests that the model developed in this study is a tool that enables short-term demand to be forecast accurately using small datasets.
All Science Journal Classification (ASJC) codes
- Information Systems
- Artificial Intelligence