需求預測是企業於供應鏈採購計劃過程中的關鍵部分，預測的準確程度將會影響供應鏈中的潛在風險，再則管理運營之重大決策基於預測的結果，所以缺乏預測準確性將會導致供應鏈成本的增加。因此，準確的需求預測對於提高企業發展速度以及分配充足的資源於生產計劃與營銷計劃皆相當重要，而不準確的需求預測將可能導致供應鏈中的原物料產生冗餘或不足之庫存，以致於需求預測的準確與否將同時影響供應鏈中相關的企業。

回顧過去文獻，學者對液晶科技產業的需求預測重點在終端消費市場，但隨著製造組裝業技術升級進步，終端顯示設備的螢幕尺寸也朝多樣發展，加上電子產品生命週期較短與競爭對手布局導致需求變化劇烈，為避免長鞭效應的影響，因此本研究將著重於背光模組上游零組件，以研究個案公司所提供的光學膜中的反射式偏光增亮膜為研究範圍，並以需求預測為研究主題，透過蒐集過去實際出貨數據來建立時間序列的預測模型，運用時間序列分析歷史數據，並建立需求預測模型，評估預測模型，比較預測模型，尋求最佳預測模型，以獲得未來需求的預測值。依本研究分析結果，使用ARIMA預測模型可以提供需求預測最小化預測誤差，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，以符合市場的需求，不僅材料供需平衡，且順利達成訂單期望交期，並持續提高客戶滿意度為主要宗旨。

Demand forecasting plays a crucial role in the process of procurement plans for a firm's supply chain. The accuracy of forecast affects the potential risks in the supply chain and the significant management decisions depending on the forecast, so the accuracy of forecast result in the increase of cost for the supply chain. Therefore, the accurate forecasting is important to elevate the speed of business development and to allocate sufficient resources to both production and marketing plans, while the inaccurate forecasting may lead to the inventory of raw materials either in surplus or in insufficient.
With the purpose to establish an optimal forecasting model for Dual Brightness Enhancement Films (DBEF) demand, there are numerous of predictive methods for demand forecasting are adopted, and time series analysis is one of well-performed methods. Since the basic rationale of time series analysis is data-driven and relatively intuitive, considering the collected data with characteristic of time series, perform timer serials analysis is verified in the study.
According to the results of analysis in this study, adopting the ARIMA model can minimize the forecast errors. Under the highly competitive economy environment, demand forecasting assists the firms to face the rapid market changes, grasp the market context, and fully understand business opportunities to satisfy the market needs. The main purpose is to balance supply and demand, to successfully achieve the expected delivery date of customer orders, and continuously improve customer satisfaction.

中文文獻
台灣明尼蘇達光電. (2020). 3M 科技改善生活™. Retrieved from https://www.3m.com.tw/3M/zh_TW/company-tw/
台灣經濟研究院. (2019). TFT-LCD面板零組件製造業發展現況與未來產業趨勢. Retrieved from https://www.tier.org.tw/achievements/pec3010.aspx?GUID=7d799b06-023e-4172-abaf-5e84de046f1c
行政院科技會報辦公室. (2020). 台灣顯示科技與應用行動計畫. Retrieved from https://www.ey.gov.tw/Page/9277F759E41CCD91/73dd8020-8877-4161-bcbd-bb8d999aa480
余桂霖. (2013). 時間序列分析. 台北: 五南圖書出版股份有限公司.
林暉雄, 鮑友南, & 游家瑋. (2008). 應用於平面顯示器之整合型光學膜片技術與發展趨勢. 科儀新知, 166, 87-97.
陳燕儀, & 呂世源. (2007). 光學膜—光的魔術師. 科學發展, 414, 62-67.
英文文獻
Amini, M. H., Karabasoglu, O., Ilić, M. D., Boroojeni, K. G., & Iyengar, S. S. (2015, 26-30 July 2015). ARIMA-based demand forecasting method considering probabilistic model of electric vehicles' parking lots. Paper presented at the 2015 IEEE Power & Energy Society General Meeting.
Amra, I. A. S. A., & Maghari, A. Y. A. (2018, 3-4 Oct. 2018). Forecasting Groundwater Production and Rain Amounts Using ARIMA-Hybrid ARIMA: Case Study of Deir El-Balah City in GAZA. Paper presented at the 2018 International Conference on Promising Electronic Technologies (ICPET).
Büyükşahin, Ü. Ç., & Ertekin, Ş. (2019). Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition. Neurocomputing, 361, 151-163.
Biwa, G., Doi, M., Yasuda, A., & Kadota, H. (2019). 11‐1: Invited Paper: Technologies for the Crystal LED Display System. Paper presented at the SID Symposium Digest of Technical Papers.
Box, G., & Jenkins, G. (1970). Time Series Analysis-Forecasting and Control. . San Francisco: Holden Day.
Caniato, F., Kalchschmidt, M., & Ronchi, S. (2011). Integrating quantitative and qualitative forecasting approaches: organizational learning in an action research case. Journal of the Operational Research Society, 62(3), 413-424.
Chang, C.-J., Yu, L., & Jin, P. (2016). A mega-trend-diffusion grey forecasting model for short-term manufacturing demand. Journal of the Operational Research Society, 67(12), 1439-1445.
Fanoodi, B., Malmir, B., & Jahantigh, F. F. (2019). Reducing demand uncertainty in the platelet supply chain through artificial neural networks and ARIMA models. Computers in Biology and Medicine, 113. Retrieved from <Go to ISI>://WOS:000496898100024. doi:10.1016/j.compbiomed.2019.103415
Fattah, J., Ezzine, L., Aman, Z., El Moussami, H., & Lachhab, A. (2018). Forecasting of demand using ARIMA model. International Journal of Engineering Business Management, 10. Retrieved from <Go to ISI>://WOS:000448972500001. doi:10.1177/1847979018808673
Huang, Y., Hsiang, E.-L., Deng, M.-Y., & Wu, S.-T. (2020). Mini-LED, Micro-LED and OLED displays: Present status and future perspectives. Light: Science & Applications, 9(1), 1-16.
Kilimci, Z. H., Akyuz, A. O., Uysal, M., Akyokus, S., Uysal, M. O., Atak Bulbul, B., & Ekmis, M. A. (2019). An improved demand forecasting model using deep learning approach and proposed decision integration strategy for supply chain. Complexity, 2019.
Lebell, D., & Krasner, O. J. (1977). Selecting Environmental Forecasting Techniques from Business Planning Requirements. The Academy of Management Review, 2(3), 373-383. Retrieved from http://www.jstor.org/stable/257694. doi:10.2307/257694
Lee, H. G., Lee, C. S., Lee, S. G., Heo, Y. J., Lim, Y. J., & Lee, S. H. (2019). P‐106: Guest‐Host Liquid Crystal Devices Utilizing Dichroic Dye and Its Application. Paper presented at the SID Symposium Digest of Technical Papers.
Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting: Butterworth-Heinemann.
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). Statistical and Machine Learning forecasting methods: Concerns and ways forward. Plos One, 13(3). Retrieved from <Go to ISI>://WOS:000428373000048. doi:10.1371/journal.pone.0194889
Mor, R. S., Jaiswal, S. K., Singh, S., & Bhardwaj, A. (2019). Demand forecasting of the short-lifecycle dairy products. In Understanding the Role of Business Analytics (pp. 87-117): Springer.
Narasimhan, B. A. (2018). Ultra-Compact pancake optics based on ThinEyes super-resolution technology for virtual reality headsets. Paper presented at the Digital Optics for Immersive Displays.
Pratyaksa, H., Permanasari, A. E., Fauziati, S., & Fitriana, I. (2016, 5-6 Oct. 2016). ARIMA implementation to predict the amount of antiseptic medicine usage in veterinary hospital. Paper presented at the 2016 1st International Conference on Biomedical Engineering (IBIOMED).
Salehzadeh, R., Tabaeeian, R. A., & Esteki, F. (2020). Exploring the consequences of judgmental and quantitative forecasting on firms' competitive performance in supply chains. Benchmarking-an International Journal, 27(5), 1717-1737. Retrieved from <Go to ISI>://WOS:000524626300001. doi:10.1108/bij-08-2019-0382
Shahjahann, A. I., & Akter, M. S. (2018). Development technique of NTSC color gamut more than 107% within Full HD resolution in LED TV display using Quantum dot film based direct type back light structure. Paper presented at the 2018 21st International Conference of Computer and Information Technology (ICCIT).
Shao, C., & Wang, L. (2010). Quantitative and Qualitative Forecasting Applied to Supply-Chain Inventory. Paper presented at the 2010 Second International Conference on Multimedia and Information Technology.
Tliche, Y., Taghipour, A., & Canel-Depitre, B. (2020). An improved forecasting approach to reduce inventory levels in decentralized supply chains. European Journal of Operational Research, 287(2), 511-527. Retrieved from <Go to ISI>://WOS:000550057300008. doi:10.1016/j.ejor.2020.04.044
Uribe, G. J. G., Guevara, D. E. R., & Gallego, P. A. R. (2018). Estimation of Residential Natural Gas Consumption in Medellin-Antioquia. Ieee Latin America Transactions, 16(3), 819-822. Retrieved from <Go to ISI>://WOS:000432210400019. doi:10.1109/tla.2018.8358661
Xin, G., Fei, D., Dong, C., Lingyu, S., Xiuyun, C., Yoon, D., . . . Zongze, H. (2017). P‐41: Development of High Luminance Curved Backlight Modules for Automotive Display Applications. Paper presented at the SID Symposium Digest of Technical Papers.
Zeng, W.-y., Xu, H.-q., Li, H., Zhang, D.-q., Zheng, L.-l., & Li, S.-j. (2020). Study on Viewing Angle Characteristics of Different Stacked Liquid Crystal Display Module. Paper presented at the SID Symposium Digest of Technical Papers.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.