由於外在環境因素的不確定性，決策者常需藉由預測模式的輔助，以對商業性運作程序做出最佳決策。在一般預測模式中，由於品牌知名度、促銷等外在變因對產品銷售量產生重大影響，而使以歷史資料為基礎之量化預測方法的準確性失真許多。據此，本研究強調同時考慮量化與質性研究方法對產品銷售量的影響，以提供一個更為準確的預測系統。
為達成此目的，本研究應用模糊神經網路(Fuzzy Neural Network, FNN)和以神經網路為輔之模糊邏輯控制與決策系統(Neural-Network-Based Fuzzy Logic Control and Decision System, NN-FLCS) 來評估影響銷售量之外在變因。此後，將質性外在變因與量化的時間序列銷售量資料整合成倒傳遞神經網路(Back Propagation Network, BPN)的輸入變項，且應用數種以人工免疫系統(Artificial Immune System, AIS)為基礎之演算法訓練BPN，以找到網路內的最適權重組合，使得預測準確度提高，並且各方法亦進行互相比較與分析。
為了評估提出的方法，本研究合作個案廠商提供某特定品牌的筆記型電腦銷售量資料及問卷調查，其研究結果顯示同時考慮量化與質性的資料將可改善預測的結果，此外，經由AIS來找尋BPN的權重組合，可增加預測準確度。

With the uncertainty of the external environment factors, forecasting model has been applied to assist decision makers to make better decision in the business process. In addition, the external factors, such as brand awareness and advertising, could significantly influence the product sales. This makes the quantitative forecasting techniques which are most based on historical sales data, lose their forecasting accuracy. Thus, the emphasis should be made to consider both quantitative and qualitative data simultaneously in order to provide a more accurate sales forecast.
In order to achieve this goal, current study employs fuzzy neural network (FNN), Neural-Network-Based Fuzzy Logic Control and Decision System (NN-FLCS), to evaluate the impact of external qualitative factors on the sales. Thereafter, this qualitative impact and time series sales data are integrated as the inputs for a back-propagation network (BPN). Furthermore, some artificial immune system (AIS)-based algorithms are used to train the back-propagation network in order to find the more appropriate connecting weights for the network with higher forecasting accuracy. The comparison among the artificial immune system-based algorithms is also conducted.
In order to assess the proposed method, a franchise computer company provided the sales data and questionnaire survey for a type of laptop computers. The computational results indicate that considering both qualitative and quantitative data really can improve the forecasting performance. In addition, through using AIS to find the connecting weights for BPN, it can provide more accurate forecasting.

中文部分
江妮蓉. 2010. 整合人工免疫系統與K-means於顧客關係管理之分群應用. 碩士, 國立臺灣科技大學.
吳家駿. 2006. 應用免疫演算法於配電系統運轉策略之研究. 碩士, 國立中山大學.
李培銘, 邱. 2008. 消費者國際展覽知覺與抱怨行為關係之研究. 商學學報, 16, 49-66.
李濤 2005. 計算機免疫學, 凡異出版社.
林妙雀, 李. 2010. 吞世代青少年品牌形象及品牌態度之研究－以同儕從眾行為為干擾變數. 行銷評論, 7, 525-556.
林信成 1990. 軟性計算理論與知識處理技術之研究. 教育資料與圖書館學, 38, 148-173.
孫佩良. 2008. 以現值觀點探討回收性產品之最佳存貨模式. 碩士, 中原大學.
留英龍. 2000. 模糊理論應用於地層下陷之預測. 碩士, 國立成功大學.
張玉瑛. 2007. 以支援向量機預測台灣地區營造工程物價指數之研究. 碩士, 朝陽科技大學.
張晉瑋. 2011. 整合人工免疫系統與最佳化人工免疫網路於倒傳遞神經網路之學習-以無線射頻辨識系統之定位為例. 碩士論文, 國立台灣科技大學.
張逸凡. 2005. 支撐向量機在即時河川水位預報之應用. 碩士, 國立成功大學.
張裴章, 張., 黃浩倫 2004. 類神經網路理論與實務, 台灣東華書局股份有限公司.
張鴻志. 2005. 整合人工免疫系統與類神經網路於製程參數最佳化之研究. 碩士, 國立雲林科技大學.
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. 碩士, 國立高雄第一科技大學.
陳寬裕, 何嘉惠 & 蕭宏誠 2004. 應用支援向量迴歸於國際旅遊需求之預測. 旅遊管理研究, 4, 81-97.
傅和彥 1999. 生產管理(第六版), 前程企業.
焦李成, 杜. 2003. 人工免疫系統進展與展望. 電子學報, 31.
黃建偉 2008. 應用灰色理論模型於汽車零件出口量預測之研究. 第九屆兩岸經貿暨管理國際學術研討會.
黃誌瑩. 2001. 教育訓練制度規劃之個案研究---以K公司為例. 碩士, 國立中央大學.
葉怡成 1995. 應用類神經網路, 儒林圖書有限公司.
葉怡成 1999. 類神經網路模式應用與實作, 儒林圖書有限公司.
葉若春 1987. 生產計劃與管制, 中興管理顧問出版.
歐宗殷. 2011. 資料探勘為基礎之零售業銷售預測模式以連鎖超商鮮食商品為例. 博士, 國立清華大學.
蔡錦裕 2005. 筆記型電腦市場地位與競爭策略之研究. 中華管理學報, 6, 17-36.
賴明勇, 林.,
孫楓林 1999. 商情預測, 五南圖書出版公司.
鍾暳陵. 2008. 廠商最適搭售行為與產品替代性. 國立東華大學.
英文部分
AAKER, D. A. 1991. Guarding the power of a brand name. New York Times.
ABDEL-AAL, R. E. 2004. Short-term hourly load forecasting using abductive networks. Power Systems, IEEE Transactions on, 19, 164-173.
BONISSONE, P. P. 2002. Hybrid Soft Computing for Classification and Prediction Applications. Proceedings of the First International Conference on Computing in an Imperfect World. Springer-Verlag.
BOX, G. E. P. & JENKINS, G. M. 1976. Time series analysis: forecasting and control, Holden-Day.
CAO, L. 2003. Support vector machines experts for time series forecasting. Neurocomputing, 51, 321-339.
CERAVOLO, F., DE FELICE, M. & PIZZUTI, S. 2009. Combining Back-Propagation and Genetic Algorithms to Train Neural Networks for Ambient Temperature Modeling in Italy Springer Berlin / Heidelberg.
CHAKRABORTY, K., MEHROTRA, K., MOHAN, C. K. & RANKA, S. 1992. Forecasting the behavior of multivariate time series using neural networks. Neural Networks, 5, 961-970.
CHANG, C.-K. 2009. Determinant Factors of Double Price Promotion Effect.
CHAO, C.-T. & TENG, C.-C. 1995. Implementation of a fuzzy inference system using a normalized fuzzy neural network. Fuzzy Sets and Systems, 75, 17-31.
CHEN, Y. & YAO, Y. 2008. A multiview approach for intelligent data analysis based on data operators. Information Sciences, 178, 1-20.
DARBELLAY, G. A. & SLAMA, M. 2000. Forecasting the short-term demand for electricity: Do neural networks stand a better chance? International Journal of Forecasting, 16, 71-83.
DASGUPTA, D. Year. Artificial neural networks and artificial immune systems: similarities and differences. In: Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on, 873-878 vol.1.
DE CASTRO, L. N. & TIMMIS, J. Year. An artificial immune network for multimodal function optimization. In: Evolutionary Computation, 2002a. 699-704.
DE CASTRO, L. N. & TIMMIS, J. 2002b. Hierarchy and Convergance of Immune Networks: Basic Ideas and Premilinary Results. 1st International Conference on Artificial Immune Systems.
DE CASTRO, L. N. & VON ZUBEN, F. (eds.) 2001. aiNET: An Artificial Immune Network for Data Analysis.
DE CASTRO, L. N. & VON ZUBEN, F. J. 2002. Learning and optimization using the clonal selection principle. Evolutionary Computation, IEEE Transactions on, 6, 239-251.
DHOLAKIA, U. M. 2000. Temptation and resistance: An integrated model of consumption impulse formation and enactment. Psychology and Marketing, 17, 955-982.
DIANE, E. K. 1990. Machine Learning. Training and Development Journal, 44, 24-29.
DONLEBELL & KRASNER, O. J. 1977. Selecting Environmental Forecasting from Business Planning Requirements. Academy of Management Review, 19, 373-383.
FORREST, S., PERELSON, A. S., ALLEN, L. & CHERUKURI, R. Year. Self-nonself discrimination in a computer. In: Research in Security and Privacy, 1994. Proceedings., 1994 IEEE Computer Society Symposium on, 16-18 May 1994 1994. 202-212.
G.PETER, Z. 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
GALEANO, J. C., SUAN, A. V. & GONZALEZ, F. A. 2005. A comparative analysis of artificial immune network models. Proceedings of the 2005 conference on Genetic and evolutionary computation. Washington DC, USA: ACM.
GHIASSI, M., SAIDANE, H. & ZIMBRA, D. K. 2009. A dynamic artificial neural network model for forecasting time series events. International Journal of Forecasting, 21, 341-362.
HARDESTY, D. M. & BEARDEN, W. O. 2003. Consumer evaluations of different promotion types and price presentations: the moderating role of promotional benefit level. Journal of Retailing, 79, 17-25.
HEILMAN CM, BOWMAN D & GP, W. 2000. The Evolution of Brand Preferences and Choice
Behaviors of Consumers New to a Market. Journal of Marketing Research. 37, 2, 139-155.
HEILMAN CM, B. D., WRIGHT GP 2000. The Evolution of Brand Preferences and Choice Behaviors of Consumers New to a Market. Journal of Marketing Research. 37, 139-155.
HOYER, W. D. A. B., S. P. 1990. Effects of brand awareness on choice for a common, repeat-purchase product. Journal of Consumer Research, 17, 141-148.
HSU, C.-C. & CHEN, C.-Y. 2003. Regional load forecasting in Taiwan––applications of artificial neural networks. Energy Conversion and Management, 44, 1941-1949.
HUNT, J. E. & COOKE, D. E. 1996. Learning using an artificial immune system. Journal of Network and Computer Applications, 19, 189-212.
ISHIBUCHI, H., KWON, K. & TANAKA, H. 1995. A learning algorithm of fuzzy neural networks with triangular fuzzy weights. Fuzzy Sets and Systems, 71, 277-293.
JAIKLA, R., AUEPHANWIRIYAKUL, S. & JINTRAWET, A. Year. Rice yield prediction using a Support Vector Regression method. In: Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2008. ECTI-CON 2008. 5th International Conference on, 14-17 May 2008 2008. 29-32.
JAMES A. FREEMAN, D. M. S. 1991. Neural Networks: Algorithms, Applications, and Programming Techniques Addison-Wesley Pub.
JANG, J. S. R. 1993. ANFIS: adaptive-network-based fuzzy inference system. Systems, Man and Cybernetics, IEEE Transactions on, 23, 665-685.
JERNE, N. 1974. Towards a network theory of the immune system. Ann Immunol (Inst Pasteur), 125C, 378-389.
KEAN, J. 1993. Neural nets and stocks: training a predictive system. PC AI, 7, 45-47.
KUO, R. J. & XUE, K. C. 1998. A decision support system for sales forecasting through fuzzy neural networks with asymmetric fuzzy weights. Decision Support Systems, 24, 105-126.
KYLE, B. 2007. Chapter 28 The Economic Analysis of Advertising. In: ARMSTRONG, M. & PORTER, R. (eds.) Handbook of Industrial Organization. Elsevier.
LABAHN, D. W., ALI, A. & KRAPFEL, R. 1996. New product development cycle time: The influence of project and process factors in small manufacturing companies. Journal of Business Research, 36, 179-188.
LECH BIREK, D. P., JOHN BOYLAN 2011. A fuzzy logic based approach to leakage forecasting in water industry. The 31st Annual International Symposium on Forecastingggg.
LEE, C. C. 1990a. Fuzzy logic in control systems: fuzzy logic controller. I. Systems, Man and Cybernetics, IEEE Transactions on, 20, 404-418.
LEE, C. C. 1990b. Fuzzy logic in control systems: fuzzy logic controller. II. Systems, Man and Cybernetics, IEEE Transactions on, 20, 419-435.
LEE, K.-M., KWAKB, D.-H. & LEEKWANG, H. 1995. Tuning of fuzzy models by fuzzy neural networks. Fuzzy Sets and Systems, 76, 47-61.
LEE, Y.-S. & TONG, L.-I. 2011. Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowledge-Based Systems, 24, 66-72.
LEONG YENG, W., BIN OMAR, J., SIAH, Y. K., ABIDIN, I. & AHMED, S. K. Year. Improvement of ANN-BP by data pre-segregation using SOM. In: Computational Intelligence for Measurement Systems and Applications, 2009. CIMSA '09. IEEE International Conference on, 11-13 May 2009 2009. 175-178.
LI, J.-B. & CHUNG, Y.-K. Year. A Novel Back-propagation Neural Network Training Algorithm Designed by an Ant Colony Optimization. In: Transmission and Distribution Conference and Exhibition: Asia and Pacific, 2005 IEEE/PES, 2005. 1-5.
LIN, C.-T. & LU, Y.-C. 1995. A neural fuzzy system with linguistic teaching signals. Fuzzy Systems, IEEE Transactions on, 3, 169-189.
LIN, C. T. & LEE, C. S. G. 1991. Neural-network-based fuzzy logic control and decision system. Computers, IEEE Transactions on, 40, 1320-1336.
LIN, S.-C. 2000. On Soft Computing Theory and Knowledge Processing Technology Journal of Educational Media and Library Sciences, 38, 148-173.
LIN, S.-W., CHEN, S.-C., WU, W.-J. & CHEN, C.-H. 2009. Parameter determination and feature selection for back-propagation network by particle swarm optimization. Knowledge and Information Systems, 21, 249-266.
LOTFI A, Z. 2001. Applied Soft Computing – Foreword. Applied Soft Computing, 1, 1-2.
NEIDHOEFER, J. C. & KRISHNAKUMAR, K. Year. Immunized neural networks for complex system identification. In: System Theory, 1993. Proceedings SSST '93., Twenty-Fifth Southeastern Symposium on, 7-9 Mar 1993 1993. 383-387.
NORMAN DALKEY, O. H. 1963. An Experimental Application of the Delphi Method to the Use of Experts. Management Science, 9, 458-467.
PARK, D. C., EL-SHARKAWI, M. A., MARKS, R. J., II, ATLAS, L. E. & DAMBORG, M. J. 1991a. Electric load forecasting using an artificial neural network. Power Systems, IEEE Transactions on, 6, 442-449.
PARK, J. H., PARK, Y. M. & LEE, K. Y. 1991b. Composite modeling for adaptive short-term load forecasting. Power Systems, IEEE Transactions on, 6, 450-457.
PASTI, R. & DE CASTRO, L. N. Year. An Immune and a Gradient-Based Method to Train Multi-Layer Perceptron Neural Networks. In: Neural Networks, 2006. IJCNN '06. International Joint Conference on, 0-0 0 2006. 2075-2082.
R.C. HWANG, H. C. H., J.G. HSIEH 2000. Short-Term Power Load Forecasting By Neural Network With Stochastic Back-Propagatioion Learning Algorithm. Power Engineering Society Winter Meeting. IEEE.
SASAKI, M., KAWAFUKU, M. & TAKAHASHI, K. Year. An immune feedback mechanism based adaptive learning of neural network controller. In: Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on, 1999 1999. 502-507 vol.2.
SHANN, J. J. & FU, H. C. 1995. A fuzzy neural network for rule acquiring on fuzzy control systems. Fuzzy Sets and Systems, 71, 345-357.
SHEN, Y.-C., CHI, C.-H. & CHEN, J.-S. 2007. A new perspective on the effects of price promotions in Taiwan: a longitudinal study of a Chinese society. International Journal of Consumer Studies, 31, 385-390.
SHIMOJIMA, K., FUKUDA, T. & HASEGAWA, Y. 1995. Self-tuning fuzzy modeling with adaptive membership function, rules, and hierarchical structure based on genetic algorithm. Fuzzy Sets Syst., 71, 295-309.
SICILIA M., R. S., REYNOLDS N. 2006. Attitude formation online: How the consumer's need for cognition affects the relationship between attitude towards the website and attitude towards the brand. International Journal of Marketing Research 2, 139-154.
TAYLOR, D. & CORNE, D. 2003. An Investigation of the Negative Selection Algorithm for Fault Detection in Refrigeration Systems. In: TIMMIS, J., BENTLEY, P. & HART, E. (eds.). Springer Berlin / Heidelberg.
TIMMIS, J. 2007. Artificial immune systems—today and tomorrow. Natural Computing, 6, 1-18.
TUVANA PASTINE , I. P. 2002. Consumption Externalities, Coordination and Advertising. International Economic Review, 43, 919-943.
VAPNIK, V. N. 1995. The nature of statistical learning theory, New York, Springer-Verlag New York.
WAKS, L. J. 2003. How Globalization Can Cause Fundamental Curriculum Change: An American Perspective. Journal of Educational Change, 4, 383-418.
WERBOS, P. J. 1974. Beyond regression: new tools for prediction and analysis in the behavioral sciences. PhD, Harvard University.
WUWEI, L. Year. Application of grey prediction theory to forecast technology input within the Chinese High-Tech Industries. In: Advanced Computer Control (ICACC), 2011 3rd International Conference on, 18-20 Jan. 2011 2011. 88-92.
YING, E. Year. Application of Support Vector Regression Algorithm in Colleges Recruiting Students Prediction. In: Computer Science and Electronics Engineering (ICCSEE), 2012 International Conference on, 23-25 March 2012 2012. 173-176.
YU-CHIUN CHIOU, M.-T. W., LAWRENCE W.LAN 2005. Coordinated Transit-preemption Signal Along An Arterial: Itherative Genetic Fuzzy Logic Controller(GFLC) Method Journal of the Eastern Asia Society for Transportation Studies, 6, 2321-2336.
ZADEH, L. A. 1975. The concept of a linguistic variable and its application to approximate reasoning. Information Sciences, 8 Parts 1-3.
ZHANG, L., WANG, Z. & ZHAO, S. 2007. Short-term fault prediction of mechanical rotating parts on the basis of fuzzy-grey optimising method. Mechanical Systems and Signal Processing, 21, 856-865.