臺灣博碩士論文加值系統

近年來，台灣的便利商店戲劇化的快速增加，便利商店的經營要面對各種不同的競爭環境。便利商店的鮮食銷售預測受到內部和外部環境的影響而具有高度的複雜性。然而，可靠的預測可以增加企業策略的品質。
本研究的目的在於開發一個混合人工智慧的便利商店鮮食銷售系統。自組織映射類神經網路和倒傳遞類神經網路被組合用以建立混合的人工模型。這個模型使用台灣某便利商店半年的鮮食銷售資料。並將本研究所提出的模型與倒傳遞類神經網路、模糊類神經網路、遺傳演算法以及線性的邏輯斯迴歸比較。結果顯示，本研究提出之模型不但可以解決過度訓練的問題和在增加資料時必須重新訓練模型的問題之外，同時也可以用來預測新的鮮食商品。

Recently, the number of Convenience Store (CVS) increases dramatically and the operation is facing various competitive environments in Taiwan. Sales forecasting of daily fresh foods of CVS is highly complex due to the influence of internal and external environments. However, reliable sales forecasting can improve the quality of business strategy.
The purpose of the study is to develop a hybrid artificial intelligent sales forecasting model of fresh foods for CVS. The Self Organization Map (SOM) neural network and Back Propagation Neural Network (BPNN) are combined to build the hybrid artificial model. The model is evaluated by a half-year sales data set of daily fresh foods of a chained CVS in Taiwan. The result of the proposed model is compared with the results of BPNN, Fuzzy Neural Network (FNN), Generic Algorithm (GA) and linear logic regression. The result reveals that the proposed model can not only solve the over fit problem and incremental data rescanning but also be used to forecast brand new fresh foods.

1. Introduction 3
2. Literature review 5
2.1 Traditional methodologies of sales forecasting 5
2.1.1 Artificial neural networks in sales forecasting 5
2.1.2 Fuzzy neural network 6
2.2 Forecasting and Sales forecasting 7
2.2.1 Statistics on Forecasting 8
2.2.2 Neural network model on Forecasting 8
2.2.3 Fuzzy model on Forecasting 8
2.3 Convenience Store (CVS) 10
3. Research Methodology 12
3.1 Hybrid Artificial Intelligent Sales Forecasting Model 12
3.1.1 CFM Procedure 12
3.1.2 SOM 13
3.1.3 BPNN 14
3.2 Data Collection 15
4. Implementation and Discussion 16
4.1 Implementation 16
4.1.1 Result of BPNN 17
4.1.2 Result of CFM 19
4.2 Discussion 19
4.2.1 Performance of BPNN 19
4.2.2 Performance of FNN 20
4.2.3 Performance of Generic Algorithm (GA) 21
4.2.4 Performance of Linear Logic Regression 21
4.2.5 Performance of CFM 23
4.2.6 Comparison of AI Method 24
5. Conclusions and Future Research 25
5.1 Conclusions 25
5.2 Future Research 25
5.3 Contribution 25
6. References 27

[1]Adamantios Diamantopoulos and Heidi Winklhofer, 2003, “Export sales forecasting by UK firms: Technique utilization and impact on forecast accuracy”, Journal of Business Research, Vol. 56, Issue 1, Pages 45-54
[2]Fader, Peter S.; Hardie, Bruce G. S, 2005, “The value of simple models in new product forecasting and customer-base analysis”, Applied Stochastic Models in Business & Industry, Vol. 21 Issue 4/5, Pages 461-473
[3]Trichy V Krishnan, V Kumar. Marketing Science. Linthicum, 2004, “Evolutionary Estimation of Macro-Level Diffusion Models Using Genetic Algorithms: An Alternative to Nonlinear Least Squares Rajkumar Venkatesan”, Expert Systems with Applications, Vol. 23, Iss. 3; Pages 451
[4]Edward J. Lusk, ,1981, “Evaluating performance statistics used to monitor performance: A fuzzy approach”, Fuzzy Sets and Systems, Vol. 5, Issue 2, Pages 149-157
[5]Pei-Chann Chang and Yen-Wen Wang , 2006, “Fuzzy Delphi and back-propagation model for sales forecasting in PCB industry”, Expert Systems with Applications, Vol. 30, Issue 4, Pages 715-726
[6]Kim, K. J., & Han, I., 2000, “Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index”, Expert Systems with Application, Vol. 19, Pages 125–132.
[7]Sebastien Thomassey and Michel Happiette, 2006, “A neural clustering and classification system for sales forecasting of new apparel items”, Applied Soft Computing, In Press, Corrected Proof
[8]Wu Wan Yi, Lin Ching He，2000, busyness research method ,Hua Tai publisher
[9]Philip Doganis, Alex Alexandridis, 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, Vol. 75, Issue 2, Pages 196-204
[10]Pei-Chann Changa and Yen-Wen Wang, 2006, “Fuzzy Delphi and back-propagation model for sales forecasting in PCB industry”, Expert Systems with Applications, Vol. 30, Issue 4, Pages 715-726
[11]Pei-Chann Chang, Yen-Wen Wang and Chen-Hao Liu, 2006, “The development of a weighted evolving fuzzy neural network for PCB sales forecasting”, Expert Systems with Applications, In Press, Corrected Proof
[12]Pei-Chann Chang, Yen-Wen Wang and Chi-Yang Tsai, 2005, “Evolving neural network for printed circuit board sales forecasting”, Expert Systems with Applications, Vol. 29, Issue 1, Pages 83-92
[13]Sebastien Thomassey and Antonio Fiordaliso, 2005, “A hybrid sales forecasting system based on clustering and decision trees”, Decision Support Systems, In Press, Corrected Proof
[14]Edward W. Frees and Thomas W. Mille, 2004, “Sales forecasting using longitudinal data models, International Journal of Forecasting”, Vol. 20, Issue 1, Pages 99-114
[15]Ching-Wu Chu and Guoqiang Peter Zhang, 2003, “A comparative study of linear and nonlinear models for aggregate retail sales forecasting”, International Journal of Production Economics, Vol. 86, Issue 3, Pages 217-231
[16]Heidi Winklhofer and Adamantios Diamantopoulos, 2003, “A model of export sales forecasting behavior and performance: development and testing”, International Journal of Forecasting, Vol. 19, Issue 2, Pages 271-285
[17]R. J. Kuo, P. Wu and C. P. Wang , 2002, “An intelligent sales forecasting system through integration of artificial neural networks and fuzzy neural networks with fuzzy weight elimination”, Neural Networks, Vol. 15, Issue 7, Pages 909-925
[18]Ralph Snyder, 2002, “Forecasting sales of slow and fast moving inventories”, European Journal of Operational Research, Vol. 140, Issue 3, Pages 684-699
[19]Heidi M. Winklhofer and Adamantios Diamantopoulos, 2002, “Managerial evaluation of sales forecasting effectiveness: A MIMIC modeling approach”, International Journal of Research in Marketing, Vol. 19, Issue 2, Pages 151-166
[20]Ilan Alon, Min Qi and Robert J. Sadowski, 2001, “Forecasting aggregate retail sales:: a comparison of artificial neural networks and traditional methods”, Journal of Retailing and Consumer Services, Vol. 8, Issue 3, Pages 147-156
[21]Derek W. Bunn and James W. Taylor, 2001, “Setting accuracy targets for short-term judgemental sales forecasting”, International Journal of Forecasting, Vol. 17, Issue 2, Pages 159-169
[22]R. J. Kuo, 2001, “A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm”, European Journal of Operational Research, Vol. 129, Issue 3, Pages 496-517
[23]R.J. Kuo, 2001, ”A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm”, European Journal of Operational Research, vol.129,Pages 496-517
[24]R.J. Kuo, S.C. Chi, S.S. Kao, 2002, “A decision support system for selecting convenience store location through integration of fuzzy AHP and artificial neural network”, Computer in industry, vol. 42, Pages 199-214
[25]Robert E. Bain bridge, MAI, SRA, 2000, “Analyzing the Market for Convenience Stores: The Changing Convenience Store Industry”, The Appraisal Journal, Pages 427-431
[26]Robert E, MAI, SRA, 2003, “Assessing Supply and Demand of Convenience Stores”, The Appraisal journal, Pages 220-226
[27]Anne Bordier, 2003, “European convenience retailing-a changing market”, European retail digest, issue 42, Pages 66-71
[28]Sebastien Thomassey and Michel Happiette, 2006, “A neural clustering and classification system for sales forecasting of new apparel items”, In Press, Corrected Proof, Available online 28 February
[29]Edward W. Frees and Thomas W. Miller, 2004, “Sales forecasting using longitudinal data models”, International Journal of Forecasting, Vol. 20, Issue 1, Pages 99-114
[30]Heidi Winklhofer and Adamantios Diamantopoulos, 2003, “A model of export sales forecasting behavior and performance: development and testing”, International Journal of Forecasting, Vol. 19, Issue 2, Pages 271-285
[31]Ralph Snyder, 2002, “Forecasting sales of slow and fast moving inventories”, European Journal of Operational Research, Vol. 140, Issue 3, Pages 684-699
[32]Derek W. Bunn and James W. Taylor, 2001, “Setting accuracy targets for short-term judgmental sales forecasting”, International Journal of Forecasting, Vol. 17, Issue 2, Pages 159-169
[33]Pei-Chann Changa and Yen-Wen Wang, 2006, “Fuzzy Delphi and back-propagation model for sales forecasting in PCB industry”, Expert Systems with Applications, Vol. 30, Pages 715-726
[34]Pei-Chann Chang, Yen-Wen Wang and Chen-Hao Liu, 2006, “The development of a weighted evolving fuzzy neural network for PCB sales forecasting”, Expert Systems with Applications, In Press, Corrected Proof
[35]Philip Doganis, etc., 2005, “Time series sales forecasting for short shelf-life food products based on artificial neural networks and evolutionary computing”, Journal of Food Engineering, Vol. 75, Pages 196-204
[36]Sebastien Thomassey and Michel Happiette, 2006, “A neural clustering and classification system for sales forecasting of new apparel items”, Applied Soft Computing, In Press, Corrected Proof
[37]Pei-Chann Chang, Yen-Wen Wang and Chen-Hao Liu, 2006, “The development of a weighted evolving fuzzy neural network for PCB sales forecasting”, Expert Systems with Applications, In Press, Corrected Proof
[38]James W. Taylor, 2007, “Forecasting daily supermarket sales using exponentially weighted quantize regression”, European Journal of Operational Research, Vol. 178, Issue 1, Pages 154-167
[39]A.S. Weigend, D.E. Rumelhart, B.A. Huberman, 1991, “Generalization by weight-elimination with application to forecasting”, Adv. Neural Inform. Process. Systems , Vol. 3, Pages 875-882
[40]Z. Tang, C. Almeida, P.A. Fishwick, 1991, “Times series forecasting using neural networks vs. Box-Jenkins methodology”, Simulations Councils, Inc., Pages 303-310
[41]K. Chakraborty, K. Mehrotra, C.K. Mohan, 1992, “Forecasting the behavior of multivariate time series using neural networks”, Neural Networks, Vol. 5, Pages 961-970
[42]G. Lachtermacher, J.D. Fuller, 1995, “Back propagation in time-series forecasting”, Journal of Forecasting, Vol. 14, Pages 381-393
[43]G.S. LeVee, 1993, “the key to understanding the forecasting process”, Journal of Business Forecasting, Vol. 11, Pages 12-16.
[44]C.W. Chase, 1993, “Ways to improve sales forecasts”, Journal of Business Forecasting, Vol. 12, Pages 15-17.
[45]M.M. Florance, M.S. Sawicz, 1993, “Positioning sales forecasting for better results”, Journal of Business Forecasting, Vol. 12, Pages 27-28.
[46]J. Kean, 1993, “Neural nets and stocks: training a predictive system”, PC AI, Pages 45 -48.
[47]J. Jarrett, 1991, “Business Forecasting Methods”, Basil Blackwell, Oxford,
[48]G.S. LeVee, 1992, “The key to understanding the forecasting process”, Journal of Business Forecasting, Vol. 11, Pages 12-16.
[49]G.G. Meyer, 1993, “Marketing research and sales forecasting at schedule corporation”, Journal of Business Forecasting, Vol. 12, Pages 22-23.