石油化學工業是世界經濟中相當重要的產業之一，大多數的石化產品之相關原物料為乙烯、丙烯和丁二烯，其佔下游產品的生產成本結構七至八成左右。特別的是，丁二烯(Butadiene, BD)為製造合成橡膠的主要原料，其最終產品大多為輪胎、鞋材、多種民生和工業用品等，然而丁二烯的價格卻經常隨著市場供需不平衡、國際經濟波動和政治事件等因素而上下震盪，造成下游廠商在採購原料時誤判價格的風險。因此，本研究以丁二烯為探討對象，若能先期準確預測原物料價格並掌握未來趨勢，將可有效協助企業降低採購成本、輔助決策，進而提升整體營運績效。
本研究提出資料科學分析架構，主要分為兩階段，第一階段為透過資料探勘技術，分別以時間序列分解、支持向量迴歸及深度學習等方法進行原物料價格預測的研究探討，並藉由量化分析供應鏈上下游的歷史價格、合約價格、產能開工率的供需以及下游替代品等多項資料建構預測模型，以提升價格及趨勢方向性之週預測準確度；第二階段則加入歷史庫存、需求和採購資料，並且考量前階段的趨勢方向性預測結果，透過強化學習技術建構採購決策模型，藉此從歷史採購經驗中學習，進而產生策略，使得整體效益最佳化，以達成價格預測輔助採購決策之目的。
本研究之實證結果表明，此分析架構可提升價格預測能力8.1%、提升趨勢方向性預測能力18.5%、降低總採購成本12.4%，並利用良好的預測結果，有效地修正採購之價格風險，進而提升企業之成本競爭優勢。

Petrochemical industry is one of the major industries in the world-wide economy. In general, ethylene, propylene and butadiene, which are associated with almost synthetic chemicals, are the main raw materials of this industry with around 70-80% cost structure. In particular, butadiene is one of the key materials for producing synthetic rubber and used for several daily commodities. However, the price of butadiene fluctuates along with the demand-supply mismatch or by the international economic fluctuations and political events. Therefore, a precise forecast of raw materials price would effectively support the company in reducing procurement costs and improving operation performances. This study proposes data science framework to predict the weekly price of butadiene by using the historical price of the butadiene industry supply chain, contract price, capacity supply rate, capacity demand rate, and downstream competitor information. Thus, this study includes two modules. One is the price prediction model with time series decomposition method, support vector regression and deep learning technique to predict weekly butadiene prices. The other module applies the analytic hierarchy process, Markov decision process and reinforcement learning technique to make a best procurement decision. An empirical study was conducted to validate the prediction and decision models, and the results show that the proposed model supports the company in raw materials procurement and provide some insights for practical decision-making process.

一、中文文獻
1. 朱則瑋，今年石化業產值 IEK預估年增上看6.2% (IEK產業情報網)，Available： http://ieknet.iek.org.tw/ieknews/news_detail.aspx?actiontype=ieknews&indu_idno=1&nsl_id=6b6dc4c65dc9476bba7ad0ce9d07ae2e (Accessed by May. 30, 2018)
2. 吳柏林，時間數列分析導論-附磁片，華泰文化，1995。
3. 李宏毅，機器學習課程上課講義，Available：http://speech.ee.ntu.edu.tw/~tlkagk/courses_ML17.html (Assessed by May.30, 2018)
4. 周秉誼，淺談Deep Learning原理及應用，國立臺灣大學計資中心電子報(C&INC E-News)，第0038期，Available：http://www.cc.ntu.edu.tw/chinese/epaper/0038/20160920_3805.html (Assessed by May.30, 2018)
5. 林建甫，台灣不該放棄石化業(IEK產業情報網)，Available：http://ieknet.iek.org.tw/ieknews/news_detail.aspx?actiontype=ieknews&indu_idno=1&nsl_id=aa88cb618c5c4bcca7f0845abd888489 (Accessed by May. 30, 2018)
6. 邱瑞麟，影響石化原料國際行情的關鍵因素探討-以丁二烯為例，國立中山大學高階經營碩士班，碩士論文，2009。
7. 美國SOLE國際物流協會台灣分會，物流與運籌管理6/e，前程文化，2016。
8. 范振誠，石化產業年鑑，工業技術研究院產業經濟與趨勢研究中心，2014。
9. 許振邦，採購與供應管理(5版)，智勝出版社，2017。
10. 曾俊樺，資料探勘技術於全基因組關聯研究:以漢族雙極症疾患為例，國立成功大學製造資訊與系統研究所，碩士論文，2016。
11. 黃子桓，Support Vector Regression，Available：http://www.cmlab.csie.ntu.edu.tw/~cyy/learning/tutorials/SVR.pdf (Accessed by May. 30, 2018)
12. 黃國展，應用類神經網路預測石化產品-丁二烯之價格，國立高雄第一科技大學運籌管理研究所，碩士論文，2012。
13. 黃塗生，晶圓代工機台採購類型及採購決策要素分析，國立交通大學科技管理學程碩士班，碩士論文，2002。
14. 經濟部工業局石化產業高值化推動專案，Available：https://www.pipo.org.tw/About/ (Accessed by May. 30, 2018)
15. 葉麗雯，供應廠產能有限及價格折扣下多產品多供應商最佳化採購決策，元智大學工業工程與管理學系，碩士論文，2003。
16. 簡禎富，決策分析與管理：紫式決策分析以全面提升決策品質（第二版），雙葉書廊，2015。
17. 簡禎富、許嘉裕，資料挖礦與大數據分析，前程文化，2014。

二、英文文獻
1. Altman, N. S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175-185.
2. Holczer, B. Random Forest Classifier – Machine Learning, Available: http://www.globalsoftwaresupport.com/random-forest-classifier-bagging-machine-learning/ (Accessed by May. 30, 2018)
3. Bellman, R. E. (1961). Adaptive control processes: a guided tour. Princeton university press.
4. Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
5. Chaharsooghi, S. K., Heydari, J., & Zegordi, S. H. (2008). A reinforcement learning model for supply chain ordering management: An application to the beer game. Decision Support Systems, 45(4), 949-959.
6. Chatterjee, S., & Hadi, A. S. (2015). Regression analysis by example. John Wiley & Sons.
7. Chien, C. F., Wu, C. H., & Chiang, Y. S. (2012). Coordinated capacity migration and expansion planning for semiconductor manufacturing under demand uncertainties. International Journal of Production Economics, 135(2), 860-869.
8. Chopra, S., & Meindl, P. (2007). Supply chain management. Strategy, planning & operation. In Das summa summarum des management (pp. 265-275). Gabler.
9. Contreras, J., Espinola, R., Nogales, F. J., & Conejo, A. J. (2003). ARIMA models to predict next-day electricity prices. IEEE transactions on power systems, 18(3), 1014-1020.
10. Drucker, H., Burges, C. J., Kaufman, L., Smola, A. J., & Vapnik, V. (1997). Support vector regression machines. In Advances in neural information processing systems (pp. 155-161).
11. Frank, R. J., Davey, N., & Hunt, S. P. (2001). Time series prediction and neural networks. Journal of intelligent and robotic systems, 31(1-3), 91-103.
12. Giannoccaro, I., & Pontrandolfo, P. (2002). Inventory management in supply chains: a reinforcement learning approach. International Journal of Production Economics, 78(2), 153-161.
13. Greenwald, A., Kannan, K., & Krishnan, R. (2010). On evaluating information revelation policies in procurement auctions: A Markov decision process approach. Information Systems Research, 21(1), 15-36.
14. Hastie, T. J., Tibshirani, R. J., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction: Springer.
15. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507.
16. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
17. Jain, C. L. (2000). Which forecasting model should we use?. The journal of business forecasting, 19(3), 2.
18. Kawakami, K. (2008). Supervised Sequence Labelling with Recurrent Neural Networks (Doctoral dissertation, Ph. D. thesis, Technical University of Munich).
19. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
20. Kohavi, R. (1995, August). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai (Vol. 14, No. 2, pp. 1137-1145).
21. Kulkarni, S., & Haidar, I. (2009). Forecasting model for crude oil price using artificial neural networks and commodity futures prices. arXiv preprint arXiv:0906.4838.
22. Lee, C. Y., & Chen, B. S. (2018). Mutually-exclusive-and-collectively-exhaustive feature selection scheme. Applied Soft Computing Journal, 68, 961-971.
23. Lee, C. Y., & Liang, C. L. (2018). Manufacturer’s Printing Forecast, Reprinting Decision, and Contract Design in the Educational Publishing Industry. Computers & Industrial Engineering.
24. Li, D. Y., Xu, W., Zhao, H., & Chen, R. Q. (2009, July). A SVR based forecasting approach for real estate price prediction. In Machine Learning and Cybernetics, 2009 International Conference on (Vol. 2, pp. 970-974). IEEE.
25. MacCallum, R. C., Widaman, K. F., Zhang, S., & Hong, S. (1999). Sample size in factor analysis. Psychological methods, 4(1), 84.
26. ML bot1. Understanding Support Vector Machines: A Primer, Available: https://appliedmachinelearning.wordpress.com/2017/03/09/understanding-support-vector-machines-a-primer/ (Accessed by May. 30, 2018)
27. Murtaza Roondiwala and Harshal Patel and Shraddha Varma. (2015). Predicting stock prices using lstm. IEEE.
28. Saaty, T. L. (1980). The Analytic Hierarchy Process:, New York, NY, McGraw Hill, reprinted by RWS Publication, Pittsburgh.
29. Saaty, T. L. (2008). Decision making with the analytic hierarchy process. International journal of services sciences, 1(1), 83-98.
30. Kaur, S. Algorithmic Trading using Reinforcement Learning augmented with Hidden Markov Model, Available: https://web.stanford.edu/class/cs221/2017/restricted/p-final/sk3391/final.pdf (Accessed by May. 30, 2018)
31. Tacq, J. J., & Tacq, J. (1997). Multivariate analysis techniques in social science research: From problem to analysis. Sage.
32. Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological), 267-288.
33. Watkins, C. J., & Dayan, P. (1992). Q-learning. Machine learning, 8(3-4), 279-292.
34. Zou, K. H., O’Malley, A. J., & Mauri, L. (2007). Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. Circulation, 115(5), 654-657.
35. Zuo, Y., & Kita, E. (2012). Stock price forecast using Bayesian network. Expert Systems with Applications, 39(8), 6729-6737.