在連鎖超商的經營管理中，管理者每日都必須預估未來的需求，並依此訂購適量的商品，過多的存貨將產生多餘的浪費，而存貨不足又可能因而失去潛在的商機，準確的預測模式將可有效地增加獲利、降低成本並有利於消費者滿意度的提升。
面對商品銷售的預測問題，連鎖超商業者莫不期望能有更好的決策支援系統來協助此項工作，以便能在快速變動的商業環境之下洞燭機先，假設管理門市的經理人能預先掌握並得知消費者對於商品的需求趨勢以及影響因子，則顧客的需求將有效地被滿足，同時報廢的商品也將大幅減少。
本研究以資料探勘的方法論建構銷售預測模式，運用灰關聯分析（Grey Relation Analysis；GRA）的特性，將影響銷售量的重要因子篩選出來，而銷售預測模式的建構則是以統計時間序列中MA、ARIMA與GARCH，以及與類神經網路中BPN、MFLN和ELM為主，並以實際的銷售資料進行預測模式的比較，預測誤差是以MSE、MAD及THEIL三項指標進行評估，所得結果顯示，本研究建構的GELM預測模式其預測能力不僅比時間序列等模式為佳，與GBPN和GMFLN相較之下，不但預測能力較佳，且訓練時間更大幅縮短。
由於活化函數與隱藏層層數將影響GELM預測模式準確度及學習速度，本研究運用田口方法中的直交表進行實驗設計，經實驗確認後證明，當隱藏層為25層並採用hardlim為活化函數時，可使GELM模式的預測誤差最小化。

Due to the strong competition that exists today, most retailers are in a continuous effort for increasing profits and reducing their cost. An accurate sales forecasting system is an efficient way to achieve the aforementioned goals and lead to improve the customers’ satisfaction, reduce destruction of products, increase sales revenue and make production plan efficiently. While manage the convenience store, the supervisor should estimate the daily demand of the future and place an order to purchase the commodities. If the managers can estimate the probable sales quantity in the next period, the demand could be satisfied and the cost of spoiled fresh foods would substantially be reduced. Besides a good forecasting model leads to improve the customers’ satisfaction, reduce destruction of fresh food, increase sales revenue and make production plan efficiently.
This study constructs a retailing sales forecasting model by data mining framework. Firstly, it applies GRA to realize the relationship between two sets of time series data in relational space then sieves out the more influential factors from raw data and transforms them as the input data for developing the forecasting model. Secondly, this research applies time series forecasting model includes MA, ARIMA, GARCH and neural network forecasting model includes BPN, MFLN and ELM. The proposed system evaluated the real sales data in the retail industry. The experimental results demonstrate that our proposed system which integrates GRA and ELM based on robust experiments design with Taguchi method outperforms than other sales forecasting methods based on time series and neural networks methodology.

中文部分
1.Philp Kotler,Siew Meng Leong,Swee Hoon Ang,Chin Tiong Tan/著。謝文雀編譯(1988)。行銷管理-亞洲實例。華泰書局。
2.William J. Stevenson著。方世榮譯(1988)。生產管理。曉園出版社。
3.William J. Stevenson著。傅和彥譯(1999)。生產管理(第六版)。前程企業。
4.中華資料採礦協會(2008)。類神經網路之心得。中華資料採礦協會研究通訊。
5.尹相志(2004)。資料採礦-網際網路應用與顧客價值管理。維科圖書有限公司。
6.方上鵬(2000)。自有品牌商品需求預測模式。東海大學工業工程研究所碩士論文
7.王淵海(1996)。統計學(上、下)。王冠出版社。
8.王琇嫻(2004)。台灣連鎖便利商店市場需求預測-迴歸模型之應用。國立成功大學企業管理研究所碩士論文。
9.王智薇(2008)。概述我國連鎖式便利商店業發展現況與展望。華南金控。
10.王樵一(2007)。通路教父徐重仁。超邁文化國際。
11.朱中亮(2002)。鮮食纇溫度控制對品質之影響。財團法人食品工業發展研究所。
12.竹內稔(1998)。21世紀連鎖便利商店實戰寶典。輝鑫出版社。
13.吳信宏、林亮宗(2003)。運用灰關聯分析於品質機能展開之決策過程:以便利商店為例。灰色系統學刊。第六卷，第二期，P.121-130。
14.李國榮(2004)。兩階段易腐性存貨訂購策略。國立雲林科技大學工業工程與管理研究所碩士論文。
15.李順益(2002)。灰色理論於短期銷售預測之適用性探討。義守大學資訊工程研究所碩士論文。
16.周湘蘭(2001)。類神經網路在多重產品需求預測上之應用。元智大學工業工程與管理研究所碩士論文
17.周鵬程(2006)。類神經網路入門-活用Matlab。 全華科技圖書股份有限公司。
18.枋立忠(2005)。設計便利商店冷藏飲品銷售預測系統。僑光技術學院管理研究所碩士論文
19.林水順、鄭志賢、蔡禎騰、彭泉、姚銘忠(2002)。資訊產品流通業之銷售預測模式分析。東海學報，43卷，p.72-88
20.林彥宏(2002)。應用平滑技術於GM(1,1)灰色模型之預測系統。大葉大學工業工程系碩士班碩士論文。
21.林清山(1988)。多變項分析統計法-社會及行為科學研究適用。台灣東華書局。
22.林傑斌、劉明德、陳湘(2002)。資料採掘與OLAP理論與實務。文魁資訊。
23.范龍生(2003)。台灣大規模連鎖便利商店鮮食商品消費者行為研究。東海大學食品科學系研究所碩士論文。
24.風華國際顧問有限公司(2008)。連銷體系的WEBPOS架構探討。2008年11月16日取自http://www.brp.com.tw/webpos
/free/pos_article_2.asp。
25.徐重仁口述。王家英整理(2004)。改變一生的相逢。聯經出版社。
26.張斐章、張麗秋(2005)。類神經網路。東華書局。
27.連英釋(2004)。便利商店鮮食商品之銷售預測模式探討-以統一超商為例。樹德科技大學經營管理研究所碩士論文。
28.郭秀敏(2003)。模糊倒傳遞網路於印刷電路板生產預測之應用。元智大學工業工程與管理研究所碩士論文
29.郭英峰、陳邦誠(2007)。以單變量ARIMA模式、類神經網路、灰色GM(1,1)模型預測高雄港貨櫃吞吐量 。臺大管理論叢，第17卷，第二期，p.107-132
30.陳功興(2006)。便利商店鮮食商品銷售預測模式之研究-探討類神經網路與平假日移動平均法的比較。國立高雄第一科技大學行銷與流通管理所碩士論文。
31.陳國隆(2001)。我國低溫食品消費與物流現況。食品市場資訊。
32.勝見明著、陳俊廷譯(2006)。巷口的商學院-在7-ELENEn上精采的企管課。先覺出版社。
33.彭克仲(2001)。運用模糊理論與灰關聯評估台灣鮮食鳳梨品質之研究。商管科技季刊。第六卷，第四期，P.345-358。
34.黃允成、楊相賢(2005)。易腐性商品在不同變異係數下最適訂購量之研究。創新與管理，第二卷，第二期，p.109-132。
35.黃仲達(2003)。灰色理論在農產銷售預測及期銷關係探討之應用。國立嘉義大學運輸與物流工程研究所碩士論文。
36.黃宜芳(1997)。鮮食經營邁向新時代。流通世界雜誌7月號 。
37.黃俊英(1986)。多變量分析第二版。中國經濟企業研究所。
38.黃秋香(2004)。2004年食品產業年鑑。財團法人食品工業發展研究所
39.黃郁仁(2003)。整合案例式推理與類神經網路於新產品銷售預測--以圖書產品為例。元智大學工業工程與管理研究所碩士論文
40.楊奕農(2005)。時間序列分析-經濟與財務上之應用。雙葉書廊有限公司
41.楊瑪利(2005)。台灣7-ELEVEN創新行銷學：每天600萬個感動。天下雜誌。
42.經濟學人著(2008)。別再扔掉垃圾食物，超市掀起「減廢」革命。天下雜誌。
43.葉怡成(2003)。應用類神經網路。儒林圖書公司。
44.葉怡成(2004)。類神經網路 - 模式應用與實作。儒林圖書公司。
45.葉若春(1987)。生產計劃與管制。中興管理顧問公司。
46.劉文祺、石智源、詹麗錦(2002)。以ARIMA結合GARCH族模式與多層函數連結網路應用於預測金融商品股價趨勢之實證研究 。產業金融季刊，第一一六期，p.22-60。
47.劉淑君(2004)。便利商店的經營模式與獲利模式之探討-以7-ELEVEn及全家便利商店為例。義守大學資訊管理學系碩士班碩士論文
48.蔡文昶(2006)。2006年食品產業年鑑-鮮食產業。財團法人食品工業發展研究所
49.鄧聚龍(1992)。灰色系統理論教程。中國華中理工大學。
50.賴明勇、林正龍、孫楓林(1999)。商情預測。五南圖書出版公司。
51.錢炳全、李順益、王學亮(2003)。基於灰色理論之短期銷售預測方法。資訊管理展望，第5卷，第一期，p.1-17。
52.謝朋昇(2008)。應用類神經網路於國產汽車銷售預測之研究。大葉大學工業工程與科技管理學系碩士在職專班碩士論文
53.羅心蓮、包曉天(2005)。比較研究臺灣地區商業電力消耗量預測模型。產業論壇。P.25-43
54.羅華強(2001)。類神經網路-MATLAB的應用。鈦思科技股份有限公司。

英文部分
1.Agrawal, D., Schorling, C., 1996. Market share forecasting: An empirical comparison of artificial neural networks and multinomial logic model. Journal of Retailing 72 (4), 383-408.
2.Akaike, H, 1974, A new look at the statistical model identification. IEEE Transactions on Automatic Control, Vol. 19, 716-723.
3.Akaike, H., 1974. A new look at the statistical model identification. IEEE Transactions on Automatic Control. Vol. 19 716-723.
4.Ansuj, A.P., Camargo, M.E., Radharamanan, R., Petry, D.G., 1996. Sales forecasting using time series and neural networks. Computers and Industrial Engineering 31 (1/2), 421-424.
5.Bigus, J.P., 1996. Data mining with neural networks: Solving business problems-from application development to decision support. McGraw-Hill, New York.
6.Bollerslev, T., 1986. Generalized Autoregressive Conditional Heteroskedasticity", Journal of Econometrics, Vol. 31, 307-327.
7.Box, G. E. P., & Jenkins, G. M. 1976. Time series analysis forecasting and control. Management Science, 17(4): 141-164.
8.C. Frank, A. Garg, L. Sztandera, A. Raheja, 2003, Forecasting women’s apparel sales using mathematical modeling. international journal of Clothing Science and Technology 15(2), 107-125.
9.C.W.Chu, G.P Zhang,2003.A comparative of linear and nonlinear models for aggregate retail sales forecasting. International journal of production economics. 86, 217-231
10.Chang, P.C., Wang, Y.W. 2006. Fuzzy Delphi and back-propagation model for sales forecasting in PCB industry. Expert Systems with Applications, 30, 715-726.
11.D. Serre, 2002, Matrices: Theory and Applications, Spinger, New York.
12.Deng, J. L., 1982. Control problems of gray systems. System Control Letter, 1(4), 288-294
13.Diane E., 1990."Machine Learning","Training & Development Journal",Vol.44, Iss.12, P.24-29
14.Engle, R. F., 1982. Auto-regressive conditional heteroscedasticity with estimates of the variance of UK inflation. Econometrical, 50, 987-1008.
15.F.L.Chen, T.Y. Ou, 2009, Grey relation analysis and multilayer function link network sales forecasting model for perishable food in convenience store. Expert Systems with Application. 36, 7054-7063.
16.G. Lachtermacher, J.D. Fuller, 1995, Back-propagation in time series forecasting. Journal of Forecasting, 14, 381-393.
17.G.B. Huang, 2003, Learning capability and strong capacity of two-hidden-layer feedforward networks. IEEE Transactions on Neural Networks, 14(2), 274-281.
18.G.B. Huang, Q.Y. Zhu, C.K. Siew, 2006, Extreme learning machine: Theory and applications. Neurocomputing, 70, 489-501.
19.Granger C.W.J., 1993. Strategies for modeling non-linear time-series relationships. The Economic Record;69:233-238.
20.Hann, T. H. and Steurer, E., 1996. “Much ado about nothing? Exchange rate forecasting: neural networks v.s. linear models using monthly and weekly data”,Harrington, L., Logistics Agent for Change: Shaping the Integrated Supply ChainNeurocomputing, pp.215-236.
21.Henson T., W. Huxhold, and D. Bowman, 1992. "An enhanced neural network learning algorithm with simulted annealing", Third Workshop on Neural Network, P.87-94
22.Hsin-His Lai, Yang-Cheng Lin Chung-Hsing Yeh, 2005, Form design of product image using grey relational analysis and neural network models. Computers & OR, 32, 2689 -2711.
23.I.Alon, M.Qi, R.J. Sadowski,2001. Forecasting aggregate retail sales: a comparison of artificial neural networks and traditional methods. Journal of reatiling and consumer services. 8, 147-156
24.J.Han, M.Kamber, 2001. Data Mining：Concepts and Techniques. A Harcourt Science and Technology Company
25.Jingtao Yao, et al., 1997. Forecasting and Analysis of Marketing Data Using Neural Networks, Nicholas, school of computing National University of Singapore.
26.K. Chakraborty, K. Mehrotra, C.K. Mohan, 1992, Forecasting the behavior of multivariate time series using neural networks. Neural Networks, 5, 961-970.
27.Kaastra I, Boyd M., 1996. Designing a neural network for forecasting financial and economic time series. Neurocomputing;10:215-236.
28.Kang S., 1991. An investigation of use of feedforward neural networks for forecasting. PhD thesis, Kent State University.
29.Kin-Fan Au, Tsan-Ming Choi, Yong Yu, 2008, Fashion retail forecasting by evolutionary neural networks. Journal of Production Economics, 114,615-630.
30.Kuo, R. J., & Chen, J. A., 2004. A decision support system for order selection in electronic commerce based on fuzzy neural network supported by real-coded genetic algorithm. Expert Systems with Application, 26(2), 141-154.
31.Kuo, R.J., 2001. A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm. European Journal of Operational Research 129,496-517
32.L.M. Sztandera, C. Frank, B. Vemulapali, 2004, Predicting women’s apparel sales by soft computing, Lecture Notes in Artificial intelligence 3070, 1193-1198.
33.Lachtermacher, G., Fuller, J.D., 1995. Backpropagation in time series forecasting. Journal of Forecasting 14, 381-393.
34.LeVee, G.S., 1993. The key to understanding the forecasting process. Journal of Business Forecasting 11 (4), 12-16.
35.Luis Aburto, Richard Weber, 2007, Improved supply chain management based on hybrid demand forecasts. Applied Soft Computing, 7,126-144.
36.Luxh, J. T., Riis, Jens. O., & Stensballe, Brain, 1996. A hybrid econometric-neural network modeling approach for sales forecasting. The International Journal of Production Economics, 43, 175-192.
37.McAvoy, T., H. Su, and P. Werbos., 1992. “Long-term predictions of chemicalprocess using recurrent neural networks: A parallel training approach”,Ind. Eng. Chem Res., Vol. 31, pp.1338-1351.
38.Özden Gür Ali, Serpil Sayin, Tom van Woensel, Jan Fransoo, 2009, SKU demand forecasting in the presence of promotions. Expert Systems with Application,36,12340-12348.
39.P.Doganis, A.Alexandridis, P.Patrinos, H.Sarimveis.2006. Time series sales forecasting for short-life food products based on artificial neural networks and evolutionary computing.Journal offood engineering. 75, 196-204
40.Peterson, R.T., Forecasting practices in the retail industry. Journal of Business Forecasting, 12, 11-14, (1993).
41.Philip Doganis, Alex Alexandrids, Panagiotis Patrinos, Haralambos Sarimveis, 2006, Time series sales forecasting for short shelf-life food products based on artificial neural networks and evolutionary computing. Journal of Food Engineering, 75, 196-204.
42.Refenes, A. N., 1993. Constructive learning and its application to currency exchange rate forecasting, Neural networks in finance and investing: using artificial intelligence to improve real-world performance, Probus Publishing Company.
43.S.Thomassey, A.Fiordaliso,2006.A hybrid sales forecasting system based on clustering and decision trees.Decision Support System.42, 408-421
44.Schawrtz, G., 1978. Estimating the Dimension of a model. Annals of Statistics;Vol.6 No. 2 461-464.
45.Sun-Tan Huang, Nan-Hsing Chiu, Li-Wei Chen, 2008, Integration of grey relational analysis with genetic algorithm for software effort estimation. European Journal of Operational Research, 188, 898-909.
46.T.J. Xiao, X.T. Qi, Price competition, cost, and demand disruption and coordination of a supply chain with one manufacturer and two competing retails. Omega 36, 741-753, (2008).
47.Taguchi, G., System of experimental design: Engineering methods to optimize quality and minimize costs. New York, NY, USA: UNIPUB. (1987).
48.Tang, Z., Almedia, C., & Fishwick, P. A., 1991. Time series forecasting using neural networks vs. Box–Jenkins methodology. Simulation, 57, 303~310.
49.Van der Vorst, J.G.A., Beulens, A. J. M., De Wit., & Van Beek, P., 1998, Supply chain management in food chains: Improving performance by reducing uncertainty. International Transactions in Operation Research, 5(6), 487-499.
50.W. Leigh, R. Purvis, J.M. Ragusa, 2002, Forecasting the NYSE composite index with technical analysis, pattern recognizer, neural network, and genetic algorithm: a case study in romantic decision support, Decision Support System, 32 (4), 361-377.
51.Weigend AS, Rumelhart DE, Huberman BA., 1991. Generalization by weight-elimination with application to forecasting. Advances in Neural Information Processing Systems;3:875-882.
52.Xiaoliang Tang and Min Han, 2009, Partial lanczos extreme learning machine for single output regression problems. Neurocomputing, doi:10.1016/ j.neucom.2009.03.016.
53.Z.L Sun, T.M Choi, K.F. Au, Y.Y,2008.Sales forecasting using extreme learning machine with applications in fashion retailing.Decision Support System.46, 411-419
54.Zhan Li Sun, Tsan Ming Choi, Kin Fan Au, Yong Yu., 2008, Sales forecasting using extreme learning machine with applications in fashion retailing. Decision Support Systems, 46, 411-419.
55.Zhang, G. P., 2003, Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
56.Zhang, G., 2001. An investigation of neural networks for linear time-series forecasting. Computers & Operations Research, 28, 183-202.
57.Zhang, G., Patuwo, E. B., & Hu, M. Y., 1998. Forecasting with artificial neural network: The state of the art. International Journal of Forecasting, 14, 35-62.