A Demand Forecasting Method on Optical Film
| Autor: | Shu-ChuanLin, 林淑娟 |
|---|---|
| Rok vydání: | 2014 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 102 The life cycle of consumer electronics are now becoming shorter, and this makes it more important than ever to forecast the demand of end users in order to minimize the bullwhip effect for supply chain vendors. The aim of this research is thus to find an appropriate model to forecast the demand for the optical films. The analysis is based on real-world data for the demand for the optical films, the costs related to TFT-LCD and the global shipping quantity of TFT-LCD, this data is then used with a time series forecast, regression forecast and artificial neural network forecast models. The accuracy of these models is then compared based on the mean absolute error, mean square error, root mean square error and mean absolute percentage error. The results show that the multiple regression model is more accurate than the artificial neural network model and time series model. The time series model is not appropriate in this context, because the demand in the optical film industry does not follow regular, cyclical variance, but instead undergoes frequent and significant changes. In addition, the artificial neural network model is not appropriate as there are not enough samples that can be divided into testing and training data. Consequently, the multiple regression model is the best one to use to forecast the demand for optical films. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|