Abstract—Forecasting accuracy significantly influences
supply chain risk. Supply chain production forecasting is very
difficult because it involves numerous upstream suppliers and
the volatility caused by the bullwhip effect through the supply
chain. The generalized autoregressive conditional
heteroskedastic (GARCH) model can handle data with
time-varying volatility. Consequently, this study is separated
into two parts for the purpose of supply chain forecasting the
production of Taiwan's TFT-LCD industry from the
perspectives of the upstream and downstream supply chain. In
the first part, three upstream components, including a
backlight module, a glass substrate, and color filter
productions were utilized to forecast TFT-LCD production
combing recurrent neural networks and genetic algorithms. In
the second part, the GARCH model was used for TFT-LCD
production prediction. The forecasting results offer valuable
references for the TFT-LCD industry. Managers can consult
the results when engaging in supply chain forecasting.
Index Terms—Forecasting, neural network, supply chain management, GARCH.
Yi-Hui Liang is with the Department of Information Management, I-Shou University (ISU), Kaohsiung City, Taiwan (e-mail: email@example.com).
Cite: Yi-Hui Liang, "Improving Production Forecasting in the Supply Chain for the TFT-LCD Industry in Taiwan," International Journal of Machine Learning and Computing vol. 10, no. 4, pp. 513-518, 2020.Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).