臺灣博碩士論文加值系統

隨著智慧型通訊裝置以及網路的蓬勃發展，讓伺服器市場成長且愈來愈重要。由於伺服器產品需求具備了前置時間長及高單價的特性，因此如何準確的預測伺服器銷售就變成重要的課題。本研究基於不同連結策略建構集群式預測模式於伺服器銷售預測。本研究所提方法先使用K-means集群技術將訓練資料予以適當分群，並針對每一個集群以支援向量迴歸(Support vector regression, SVR)及極限學習機(Extreme learning machine, ELM)建構預測模式。接著針對待預測資料，分別以中心法（Centroid linkage method）、中位數法（Median linkage method）以及遠鄰法（Furthest neighbor linkage）等三個不同的連結法(Linkage method)計算待預測資料與訓練資料子集群所對應的距離，以找到最合適於待預測資料的對應子集群，最後以對應子集群的SVR及ELM模式產生最後的預測結果。本研究以台灣某伺服器品牌商的實際伺服器銷售資料為實證資料。實證結果顯示結合遠鄰法與SVR的集群式預測模式能產生最佳的預測績效，較單純SVR、單純ELM、其他五個集群式銷售預測模式，以及實務運作上常見Seasonal Naive方法更適用於伺服器銷售預測。

Sales forecasting is crucial for every company since it is an important task for manufacturing, inventory management and marketing. In this study, a computer server sales forecasting model using clustering method with support vector regression (SVR) and extreme learning machine (ELM) with different linkage strategies is proposed. The proposed scheme first uses k-means algorithm to partition the whole training sales data into several disjoint clusters. Then, for each group, the SVR and ELM is applied to construct forecasting model. Finally, for a given testing data, three linkage methods are used to find the cluster which the testing data belongs to and then employee the corresponding trained SVR model and ELM model to generate prediction result.
A real data of computer server sales collected from a Taiwanese multinational electronics company is used as illustrative examples to evaluate the performance of the proposed model. Experimental results revealed that the proposed clustering-based sales forecasting scheme outperforms the single method and seasonal naive forecasting models and hence is an effective alternative for sales forecasting.

摘　　要 i
Abstract ii
目　　錄 iii
表目錄 v
圖目錄 vi
第一章　緒論 1
1.1　研究背景與動機 1
1.2　研究目的 2
第二章　文獻探討 3
2.1　銷售預測 3
2.2　支援向量迴歸 4
2.3 極限學習機 5
2.4 K-means集群技術 5
2.5 集群式預測 6
第三章 研究方法 8
3.1　K-means 8
3.2　連結法 8
3.3　支援向量迴歸 10
3.3.1 支援向量迴歸之基本架構 10
3.3.2 支援向量迴歸之最適化問題 11
3.3.3 支援向量迴歸之參數設定 12
3.4 極限學習機 13
3.5 所提之集群式預測模式 15
第四章 實證結果分析 22
4.1 實證資料 22
4.2. 單純預測模式實證結果 24
4.2.1 Seasonal Naive Forecasting 24
4.2.2 單純SVR預測模式 24
4.2.3 單純ELM預測模式 25
4.2.4 各單純預測模式之預測結果 26
4.3 不同連結法下的集群式預測模式之結果 27
4.4 整體比較 32
第五章 結論與建議 37
5.1 結論 37
5.2 未來研究建議 38
參考文獻 38

1. 吳萬益，企業研究方法，華泰文化出版社，台北，民國一百年。
2. 陳東和，「運用資料採礦技術於銀行基金客戶分群之研究」，私立中國文化大學資訊管理研究所，碩士論文，台北市，民國九十七年。
3.Badge, J., &; Srivastava, N. “Selection and forecasting of stock market patterns using K-mean clustering”, International Journal of Statistics and Systems, 5, pp. 23-27,&;#8232;2010.
4. Cao, L. “Support vector machines experts for time series forecasting”, Neurocomputing, 51, pp. 321-339, 2003.
5.Chang, P. C., &; Lai, C. Y. “A hybrid system combining self-organizing maps with case- based reasoning in wholesaler''s new-release book forecasting”, Expert Systems with Applications, 29(1), pp. 183-192 , 2005.
6. Chang, P. C., Liu, C. H., &; Fan, C. Y. “Data clustering and fuzzy neural network for sales forecasting: A case study in printed circuit board industry”, Knowledge-Based Systems, 22, pp. 344-355, 2009.
7.Chang, P. C., Wang, Y. W., &; Tsai, C. Y. “Evolving neural network for printed circuit board sales forecasting”, Expert Systems with Applications, 29, pp. 83-92, 2005.
8. Chen, F. L., &; Ou, T. Y. “Sales forecasting system based on Gray extreme learning machine with Taguchi method in retail industry”, Expert Systems with Applications, 38, pp. 1336-1345, 2011.
9. Chen, L. Y. “Application of SVR with chaotic GASA algorithm to forecast Taiwanese 3G mobile phone demand”, Neurocomputing, 127, pp. 206-213, 2014.
10. Cherkassky, V., &; Ma, Y. “Practical selection of SVM parameters and noise estimation for SVM regression”, Neural Networks, 17, pp. 113-126, 2004.
11.Duan, P., Xie, K., Guo, T., &; Huang, X. “Short-term load forecasting for electric power systems using the PSO-SVR and FCM clustering techniques”, Energies, 4(1), pp. 173-184, 2011.
12.Godehardt, E., Graphs as structural models: the application of graphs and multigraphs in cluster analysis, Vieweg, Braunschweig,1988.
13.Gunn, S. R. “Support vector machines for classification and regression”, ISIS technical &;#8232;report, 14, 1998.
14.Hong, W. C., Dong, Y., Chen, L. Y. &; Lai, C. Y. “Taiwanese 3G mobile phone demand forecasting by SVR with hybrid evolutionary algorithms”, Expert Systems with Applications, 37, pp. 4452-4462, 2010
15.Hong, W. C., Dong, Y. C., Chen, L. Y., &; Wei, S. Y. “SVR with hybrid chaotic genetic &;#8232;algorithms for tourism demand forecasting”, Applied Soft Computing, 11(2), pp. 1881- &;#8232;1890, 2011.
16.Huang, G. B., Zhu, Q.Y., &; Siew, C.K. “Extreme learning machine: theory and applications”, Neurocomputing, 70,pp. 489-501 , 2006.
17.Hyunchul, A., Eunsup, C., &; Ingoo, H. “Extracting underlying meaningful features and canceling noise using independent component analysis for direct marketing”, Expert Systems with Applications, 33, pp. 181-191 , 2007.
18.Jiang, H., &; Wang, Z. H. “GMRVVm–SVR model for financial time series forecasting”, Expert Systems with Applications, 37, pp. 7813-7818, 2010.
19.Kai, C., Fu, F. P., &; Che.,W.G. “Notice of Retraction A Novel Forecasting Model of Fuzzy Time Series Based on K-means Clustering”, In Education Technology and Computer Science (ETCS), 1, pp. 223-225. Wuhan, China, March, 2010.
20.Kuo, R. J. “A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm”, European Journal of Operational Research, 129, pp. 496-517, 2001.
21.Lan, Y., Soh, Y. C., &; Huang, G. B. “Two-stage extreme learning machine for regression”, &;#8232;Neurocomputing, 73(16), pp. 3023-3038, 2010.
22.Levis, A. A., &; Papageorgiou, L. G. “Customer demand forecasting via support vector &;#8232;regession analysis”, Chemical Engineering Research and Design, 83(8), pp. 1009-1018, 2005.
23.Lu, X., &; Geng, X. “Car Sales Volume Prediction Based on Particle Swarm Optimization Algorithm and Support Vector Regression”, Intelligent Computation Technology and Automation (ICICTA), pp. 71-74, Shenzhen, Guangdong, China, March, 2011.
24.Martinez-Alvarez, F. “Clustering preprocessing to improve time series forecasting”, AI Communications, 24(1), pp. 97-98, 2011.
25.Ni, H., &; Yin, H. “Exchange rate prediction using hybrid neural networks and trading indicators”, Neurocomputing, 72(13), pp. 2815-2823, 2009.
26.Pan, F., Zhang, H., &; Xia, M. “A hybrid time-series forecasting model using extreme learning machines”, Intelligent Computation Technology and Automation (ICICTA), pp. 933-936 , Changsha, Hunan, China, Oct, 2009.
27.Punj, G., &; Stewart, D. W. “Cluster analysis in marketing research: review and suggestions for application”, Journal of marketing research, 20, pp. 134-148, 1983.
28.Qiao, M. Y., Ma, X. P., Lan, J. Y., &; Wang, Y. “Time-series gas prediction model using LS-SVR within a Bayesian framework”, Mining Science and Technology, 21, pp. 153-157, 2011.
29.Sun, Z. L., Choi, T. M., Au, K. F., &; Yu, Y. “Sales forecasting using extreme learning machine with applications in fashion retailing”, Decision Support Systems, 46, pp. 411-491, 2008.
30.Tan, J. Y. B., Bong, D. B. L., &; Rigit, A. R. H. “Time Series Prediction using Backpropagation Network Optimized by Hybrid K-means-Greedy Algorithm”, Engineering Letters, 20(3),pp. 203-210, 2012.
31.Taylor, J. W. “Forecasting daily supermarket sales using exponentially weighted quantile regression”, European Journal of Operational Research, 178, pp. 154-167, 2007.
32.Thomassey, S., &; Happiette, H. “A neural clustering and classification system for sales forecasting of new apparel items”, Applied Soft Computing, 7(4), pp. 1177-1187, 2007.
33.Vapnik, V., Golowich, S. E., &; Smola, A. “Support vector method for function approximation, regression estimation and signal processing”, Advance in Neural Formation processing system, 9, pp. 281-287 , 1997.
34.Yu, Y., Choi, T. M., &; Hui, C. L. “An intelligent fast sales forecasting model for fashion products”, Expert Systems with Applications, 38(6), pp. 7373-7379 , 2011.
35.Zhang, J., &; Yang, Y. “BP Neural Network Model Based on the K-Means Clustering to Predict the Share Price”, Computational Sciences and Optimization (CSO), pp. 181-184, Harbin, China, June, 2012.
36.Zhang, Z., &; Zhu, Q. “Fuzzy Time Series Forecasting Based On K-Means Clustering”, Open Journal of Applied Sciences, 2(04), pp. 100-103, 2013.