液晶電視要顯示出高畫質畫面，少不了各式各樣的光學膜，回顧過去文獻，學者對TFT-LCD需求的研究，僅著重在最終產品的需求預測，隨著電子產品生命週期的縮短與日益劇烈的競爭導致下游需求變動頻繁，一旦前線業務人員的資訊失真或資訊被曲解，企業內部常常反應不及，使得生產、存貨以及配送規劃皆造成問題，甚至會造成極大損失。
本研究聚焦於背光模組上游零組件之的需求預測，本研究以光學膜供應商的需求預測為主題，研究方法分別使用時間序列法、迴歸分析法以及類神經網路，建立不同的需求預測模型，並以平均絕對誤差、均方誤差、均方根誤差與平均絕對百分比誤差等四個評估準則，評估不同預測模型分別比較其預測結果，尋求最佳預測模型。盼研究結果能最小化總預測誤差，在經濟環境高度競爭下，幫助企業面對市場的快速變動，掌握市場脈絡，充份瞭解商機，維持健康庫存以支持客戶需求。
本研究蒐集光學膜實際出貨量、面板市場價格與全球面板出貨量作為預測變數來進行模式建構以及驗證，研究結果發現時間序列法、迴歸分析法以及類神經網路所建立的模型之中，因光電產需求變化大再加上驗證樣本不足，因此複迴歸在預測績效表現優於時間序列分析法以及類神經網路。

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.

參考文獻
中文文獻
于宗先. (民61). 經濟預測. 台北市: 大中國圖書有限公司.
田大昌, 溫景發, 林麗娟 & 劉文亮. (民95). LCD反射式增亮膜(DBEF)之微結構分析. 工業材料雜誌, 232, 137-143.
光電科技協進會編輯部. (民100). Display─all NO.23. 不可或缺的關鍵一片　科技綠潮的發展無限　3M光學增亮膜傳奇, pp. 25-27.
張偉哲, 溫坤禮 & 張政廷. (民89). 灰關聯模型方法與應用. 台北市: 高立圖書公司.
郭明哲. (民65). 預測方法-理論與實務. 台北市: 中興管理顧問公司.
楊奕農. (民94). 時間序列分析：經濟與財務上之應用 第二版. 台北市: 雙葉書廊.
Jay C. (民102). 3M 光學增亮膜技術，提高螢幕亮度，減少背光耗電。民102年11月21日。取自：http://jay506.pixnet.net/blog
MoneyDJ理財網財經知識庫. 財經百科-稜鏡片(BEF) 。民102年10月18日。取自：http://www.moneydj.com/ kmdj/wiki/wikiviewer. aspx? Key ID=4c98d7fd-320c-4c68-a14b-c7ec30d91df2
英文文獻
Abraham G., Byrnes G. B. & Bain C. A. (2009). Short-Term Forecasting of Emergency Inpatient Flow. Ieee Transactions on Information Technology in Biomedicine, 13(3), 380-388.
Affijulla S. & Chauhan S. (2011). A new intelligence solution for power system economic load dispatch. 2011 10th International Conference on Environment and Electrical Engineering (EEEIC), 5 pp.-5 pp.
Azadeh A., Saberi M. & Seraj O. (2010). An integrated fuzzy regression algorithm for energy consumption estimation with non-stationary data: A case study of Iran. Energy, 35(6), 2351-2366.
Bianco V., Manca O. & Nardini S. (2009). Electricity consumption forecasting in Italy using linear regression models. Energy, 34(9), 1413-1421.
Box G. E. P. & Jenkins G. (1970). Time Series Analysis: Forecasting and Control. San Francisco: Holden-Day.
Cao Q., Ewing B. T. & Thompson M. A. (2012). Forecasting wind speed with recurrent neural networks. European Journal of Operational Research, 221(1), 148-154.
Cho V. (2003). A comparison of three different approaches to tourist arrival forecasting. Tourism Management, 24(3), 323-330.
Chopra S. & Meindl P. (2001). Supply Chain Management: Strategy, Planning, and Operation. New York: Prentice Hall.
Crone S. F., & Kourentzes N. (2010). Feature selection for time series prediction - A combined filter and wrapper approach for neural networks. Neurocomputing, 73(10-12), 1923-1936.
Lebell D. & Krasner O.J. (1977). Selecting Environmental Forecasting from Business Planning Requirements. Academy of Management Review, 373-383.
Gonzalez-Romera E., Jaramillo-Moran M. A. & Carmona-Fernandez D. (2008). Monthly electric energy demand forecasting with neural networks and Fourier series. Energy Conversion and Management, 49(11), 3135-3142.
Grubb H. & Mason A. (2001). Long lead-time forecasting of UK air passengers by Holt-Winters methods with damped trend. International Journal of Forecasting, 17(1), 71-82.
Herrera M., Torgo L., Izquierdo J. & Perez-Garcia R. (2010). Predictive models for forecasting hourly urban water demand. Journal of Hydrology, 387(1-2), 141-150.
Jones G. R. & George J. M. (2009). Essentials of Contemporary Management. New York: McGraw-Hill.
Kandil N., Wamkeue R., Saad M.& Georges S. (2006). An efficient approach for short term load forecasting using artificial neural networks. International Journal of Electrical Power & Energy Systems, 28(8), 525-530.
Kao L. J., Chiu C. C., Lu C. J. & Yang J. L. (2013). Integration of nonlinear independent component analysis and support vector regression for stock price forecasting. Neurocomputing, 99, 534-542.
Li Bo., Li J., Li W. & Shirodkar S. A. (2012). Demand forecasting for production planning decision-making based on the new optimised fuzzy short time-series clustering. Production Planning & Control, 23(9), 663-673.
Lu C. J., Lee T. S. & Lian C. M. (2012). Sales forecasting for computer wholesalers: A comparison of multivariate adaptive regression splines and artificial neural networks. Decision Support Systems, 54(1), 584-596.
Makridakis S. & Hibon M. (2000). The M3-Competition: results, conclusions and implications. International Journal of Forecasting, 16(4), 451-476.
Manda P., Senjyu T., Naomitsu U. & Funabashi T. (2006). A neural network based several-hour-ahead electric load forecasting using similar days approach. International Journal of Electrical Power & Energy Systems, 28(6), 367-373.
Nguyen H. T. & Nabney I. T. (2010). Short-term electricity demand and gas price forecasts using wavelet transforms and adaptive models. Energy, 35(9), 3674-3685.
Russel R.S. & Taylor B. W. (2000). Operations Management. New Jersey: Prentice Hall.
Shao Y. E. (2013). Prediction of Currency Volume Issued in Taiwan Using a Hybrid Artificial Neural Network and Multiple Regression Approach. Mathematical Problems in Engineering.
Taylor J. W., McSharry P. E. & Buizza R. (2009). Wind Power Density Forecasting Using Ensemble Predictions and Time Series Models. Ieee Transactions on Energy Conversion, 24(3), 775-782.
Xia C., Wang J. & McMenemy K. (2010). Short, medium and long term load forecasting model and virtual load forecaster based on radial basis function neural networks. International Journal of Electrical Power & Energy Systems, 32(7), 743-750.
Yalcinoz T. & Eminoglu U. (2005). Short term and medium term power distribution load forecasting by neural networks. Energy Conversion and Management, 46(9-10), 1393-1405.