全球對於電子性產品的大量需求，帶動著半導體產業的快速發展。而零組件通路商在供應鏈中游扮演重要的角色，須給予下游穩定的需求供給，同時也需要控制庫存水位以降低存貨持有成本。本研究目標為利用機器學習方法，預測未來下游客戶廠區的產品需求，以幫助通路商提前規劃其訂貨策略。

本研究與亞洲最大的半導體零組件通路商(簡稱W公司)進行合作，使用過往下游客戶實際取貨(Call-off)去預測未來需求。經過資料探索，我們發現有主要兩個問題：整體資料因產品需求特性，呈現高度稀疏性、變異性，本研究針對以上問題，提出解決方法。首先，針對資料的高度稀疏性，我們設定了不同的預測區間，並使用時間聚合方法將資料顆粒度放大，降低資料稀疏程度，希望進而提升預測績效；針對不同產品的高變異性資料，我們使用集群方法將各產品做分組，組內的產品因擁有相似的需求特性，能夠更好地配適機器學習模型；最後使用不同的機器學習模型(XGBoost, SVM, Deep Neural Network)進行預測。期望找出最佳的需求預測資料組合模式，期望能幫助合作公司提升預測準確度，為半導體產業鏈帶來一些新的需求預測方法進行參考。

As the high demand for electronic products has driven the development of the semiconductor industry, distributors play an important role in the supply chain because they need to meet downstream customer demand and control inventory levels to lower holding costs. The goal of this study is to use machine learning methods to predict future demand from downstream customers’ plants to help distributors schedule ordering policies.

The study cooperates with Asia’s largest semiconductor component distributor (referred to as W Company) and uses its historical data to implement demand forecasting. We find two problems during the exploratory data analysis: high sparsity
and high volatility due to the characteristics of customer demand. We solve problems by proposing a framework that includes temporal aggregation to lower data sparsity and grouping policies across different products to lower volatility and better fit machine learning models. We then employ three machine learning models — XGBoost, SVM, and Deep Neural Network — with different parameter settings. Our goal is to find the best forecasting combinations that are better than W company’s original method (8WMA).

Abolghasemi, M., Beh, E., Tarr, G., and Gerlach, R. 2020. "Demand Forecasting in Supply Chain: The Impact of Demand Volatility in the Presence of Promotion," Computers & Industrial Engineering (142), p. 106380.
Aburto, L., and Weber, R. 2007. "Improved Supply Chain Management Based on Hybrid Demand Forecasts," Applied Soft Computing (7:1), pp. 136-144.
Al-Bakri, N. F., & Hashim, S. H. (2018). Reducing data sparsity in recommender systems. Al-Nahrain Journal of Science, 21(2), pp. 138-147.
Anderson Jr, E. G., Fine, C. H., & Parker, G. G. (2000). Upstream volatility in the supply chain: The machine tool industry as a case study. Production and Operations Management, 9(3), pp. 239-261.
Berndt, D. J., and Clifford, J. 1994. "Using Dynamic Time Warping to Find Patterns in Time Series," KDD workshop: Seattle, WA, USA:, pp. 359-370.
Bissmark, J., and Wärnling, O. 2017. "The Sparse Data Problem within Classification Algorithms: The Effect of Sparse Data on the Naïve Bayes Algorithm."
Box, G. E., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. 2015. Time Series Analysis: Forecasting and Control. John Wiley & Sons.
Boylan, J. E., Syntetos, A. A., and Karakostas, G. C. 2008. "Classification for Forecasting and Stock Control: A Case Study," Journal of the operational research society (59:4), pp. 473-481.
Brown, R. G., and Meyer, R. F. 1961. "The Fundamental Theorem of Exponential Smoothing," Operations Research (9:5), pp. 673-685.
Cachon, G. P., and Lariviere, M. A. 2001. "Contracting to Assure Supply: How to Share Demand Forecasts in a Supply Chain," Management science (47:5), pp. 629-646.
Carbonneau, R., Laframboise, K., and Vahidov, R. 2008. "Application of Machine Learning Techniques for Supply Chain Demand Forecasting," European Journal of Operational Research (184:3), pp. 1140-1154.
Chatfield, C. 2000. Time-Series Forecasting. CRC press.
Chen, T., and Guestrin, C. 2016. "Xgboost: A Scalable Tree Boosting System," Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794.
Chien, C.-F., Chen, Y.-J., and Peng, J.-T. 2010. "Manufacturing Intelligence for Semiconductor Demand Forecast Based on Technology Diffusion and Product Life Cycle," International Journal of Production Economics (128:2), pp. 496-509.
Crook, T. R., and Combs, J. G. 2007. "Sources and Consequences of Bargaining Power in Supply Chains," Journal of operations management (25:2), pp. 546-555.
Ferreira, K. J., Lee, B. H. A., and Simchi-Levi, D. 2016. "Analytics for an Online Retailer: Demand Forecasting and Price Optimization," Manufacturing & Service Operations Management (18:1), pp. 69-88.
Gardner, E. S. 1990. "Evaluating Forecast Performance in an Inventory Control System," Management Science (36:4), pp. 490-499.
Gonçalves, J. N., Cortez, P., Carvalho, M. S., and Frazão, N. M. 2021. "A Multivariate Approach for Multi-Step Demand Forecasting in Assembly Industries: Empirical Evidence from an Automotive Supply Chain," Decision Support Systems (142), p. 113452.
Hill, T., O'Connor, M., and Remus, W. 1996. "Neural Network Models for Time Series Forecasts," Management science (42:7), pp. 1082-1092.
Jha, A., Ray, S., Seaman, B., and Dhillon, I. S. 2015. "Clustering to Forecast Sparse Time-Series Data," 2015 IEEE 31st International Conference on Data Engineering: IEEE, pp. 1388-1399.
Kim, K.-j. 2003. "Financial Time Series Forecasting Using Support Vector Machines," Neurocomputing (55:1-2), pp. 307-319.
Kleijnen, J. P., and Smits, M. T. 2003. "Performance Metrics in Supply Chain Management," Journal of the operational research society (54:5), pp. 507-514.
Lee, H. L., Padmanabhan, V., and Whang, S. 1997. "Information Distortion in a Supply Chain: The Bullwhip Effect," Management science (43:4), pp. 546-558.
Makridakis, S., Spiliotis, E., and Assimakopoulos, V. 2018. "Statistical and Machine Learning Forecasting Methods: Concerns and Ways Forward," PloS one (13:3), p. e0194889.
Meddahi, N., and Renault, E. 2004. "Temporal Aggregation of Volatility Models," Journal of Econometrics (119:2), pp. 355-379.
Müller, M. 2007. "Dynamic Time Warping," Information retrieval for music and motion), pp. 69-84.
Murray, P. W., Agard, B., and Barajas, M. A. 2015. "Forecasting Supply Chain Demand by Clustering Customers," IFAC-PapersOnLine (48:3), pp. 1834-1839.
Nikolopoulos, K., Syntetos, A. A., Boylan, J. E., Petropoulos, F., and Assimakopoulos, V. 2011. "An Aggregate–Disaggregate Intermittent Demand Approach (Adida) to Forecasting: An Empirical Proposition and Analysis," Journal of the Operational Research Society (62:3), pp. 544-554.
Noble, W. S. 2006. "What Is a Support Vector Machine?," Nature biotechnology (24:12), pp. 1565-1567.
Pappas, S. S., Ekonomou, L., Karamousantas, D. C., Chatzarakis, G., Katsikas, S., and Liatsis, P. 2008. "Electricity Demand Loads Modeling Using Autoregressive Moving Average (Arma) Models," Energy (33:9), pp. 1353-1360.
Pfeffer, J., and Pfeffer, J. 1981. Power in Organizations. Pitman Marshfield, MA. Reinsel, G. C., and Ahn, S. K. 1992. "Vector Autoregressive Models with Unit Roots and Reduced Rank Structure: Estimation. Likelihood Ratio Test, and Forecasting," Journal of time series analysis (13:4), pp. 353-375.
Rostami‐Tabar, B., Babai, M. Z., Syntetos, A., and Ducq, Y. 2013. "Demand Forecasting by Temporal Aggregation," Naval Research Logistics (NRL) (60:6), pp. 479-498.
Schmidhuber, J. 2015. "Deep Learning in Neural Networks: An Overview," Neural networks (61), pp. 85-117.
Senin, P. 2008. "Dynamic Time Warping Algorithm Review," Information and Computer Science Department University of Hawaii at Manoa Honolulu, USA (855:1-23), p. 40.
Syntetos, A. A., and Boylan, J. E. 2005. "The Accuracy of Intermittent Demand Estimates," International Journal of forecasting (21:2), pp. 303-314.
Terwiesch, C., Ren, Z. J., Ho, T. H., and Cohen, M. A. 2005. "An Empirical Analysis of Forecast Sharing in the Semiconductor Equipment Supply Chain," Management science (51:2), pp. 208-220.
Teunter, R. H., Syntetos, A. A., and Babai, M. Z. 2011. "Intermittent Demand: Linking Forecasting to Inventory Obsolescence," European Journal of Operational Research (214:3), pp. 606-615.
Van Steenbergen, R., and Mes, M. R. 2020. "Forecasting Demand Profiles of New Products," Decision support systems (139), p. 113401.
Wang, C.-H., and Chen, J.-Y. 2019. "Demand Forecasting and Financial Estimation Considering the Interactive Dynamics of Semiconductor Supply-Chain Companies," Computers & Industrial Engineering (138), p. 106104.
Willemain, T. R., Smart, C. N., Shockor, J. H., and DeSautels, P. A. 1994.
"Forecasting Intermittent Demand in Manufacturing: A Comparative Evaluation of Croston's Method," International journal of forecasting (10:4), pp. 529-538.
Willmott, C. J., and Matsuura, K. 2005. "Advantages of the Mean Absolute Error (Mae) over the Root Mean Square Error (Rmse) in Assessing Average Model Performance," Climate research (30:1), pp. 79-82.
Winters, P. R. 1960. "Forecasting Sales by Exponentially Weighted Moving Averages," Management science (6:3), pp. 324-342.
Zhao, X., Xie, J., and Wei, J. C. 2002. "The Impact of Forecast Errors on Early Order Commitment in a Supply Chain," Decision Sciences (33:2), pp. 251-280.
Zheng, H., Yuan, J., and Chen, L. 2017. "Short-Term Load Forecasting Using EmdLstm Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation," Energies (10:8), p. 1168.
Zhu, X., Ninh, A., Zhao, H., and Liu, Z. 2021. "Demand Forecasting with Supply‐Chain Information and Machine Learning: Evidence in the Pharmaceutical Industry," Production and Operations Management (30:9), pp. 3231-3252.