汽車銷售需求預測是國家經濟發展的重要議題之一，考量的時間數列模型的變數有汽車銷售量、景氣同時指標、景氣領先指標、原油躉售物價以及工業及服務業平均薪資等等。本研究針對台灣地區汽車新車銷售，使用月份銷售型態資料，而總汽車銷售量分類為（小客車、商用車3.5噸以下、商用車3.5噸以上）三種銷售數量，因此，本研究分成兩階層進行預測。
首先，使用逐步迴歸方法選擇出影響汽車銷售較顯著之變數作為時間數列模型之輸入變數，接著使用三種時間數列模型Box-Jenkins模型（Autoregressive Integrated Moving Average Model，ARIMA）、類神經網路模型（Artificial Neural Network，ANN）與適應性模糊類神經推論系統（Adaptive Network-Based Fuzzy Inference System，ANFIS）去預測各階層之汽車銷售量。在使用三種時間數列模型之下，其實證結果顯示，利用適應性模糊類神經推論系統（ANFIS）優於其它兩種預測方法。

關鍵字：汽車銷售、ARIMA、ANN、ANFIS、時間序列、預測

The demand forecasting of automobile sales is one of critical issues for national economic growth. Our model considers several variables such as current automobile sales quantity, coincident indicator, leading indicator, wholesale price index and income. Here, we only focus on new automobile sales in Taiwan. The data set is based on monthly sales which the data can be divided into three types of automobile sales. Thus, there are two levels in this study.
First, we use the stepwise method to select most influential variables as our input variables. Then, we use three forecasting models: ARIMA (Autoregressive Integrated Moving Average Model), ANN（Artificial Neural Network）and ANFIS(Adaptive Network-Based Fuzzy Inference System) to forecast the automobile sales in each level. We use three forecasting models to compare their forecasting performance. The conclusion shows that the ANFIS model outperforms other two forecasting models.

Key words: Automobile Industry, ARIMA, ANN, ANFIS, Time Series, Forecasting

參考文獻
中文部分
1. 于宗先，經濟預測，大中國出版社，1972。
2. 仇士元，「加總模型的預測效果-以台灣地區汽車銷售量資料為例」，長庚大學企業管理系碩士論文，2003。
3. 方世杰，預測方法一百種，書泉出版社，1988。
4. 王進德，「類神經網路與模糊控制理論入門與應用」，全華科技出版社，2007。
5. 朱延智，「產業分析」，五南圖書出版公司，2008。
6. 呂學慶，「台灣地區汽車市場銷售預測之探討」，國立中央大學管理學院高階主管企管碩士論文，2002。
7. 林茂文，「時間數列分析與預測」，華泰書局，1992。
8. 徐桂祥，「灰色系統在商情預測上之研究」，國立雲林科技大學資訊管理技術研究所碩士論文，2007。
9. 張辰彰，「我國汽車業合併經可行性研究」，國立政治大學企業管理研究所碩士論文，2000。
10. 梁肇彥，「台灣汽車產業需求預測及季節指數之研究-以ARIMA季節相乘模式分析」，國立交通大學管理學院碩士論文，2004。
11. 陳慧瀅，「台灣地區汽車場需求預測之實證-無母數雲狀迴歸加法性模型之運用」，國立中央大學產業經濟研究所碩士論文，1984。
12. 趙嬙 (2003)，「灰色預測理論應用於汽車產業預測之研究-以台灣、大陸市場為例」，朝陽科技大學企業管理系碩士論文，2003。
13. 劉佳穎，「國產汽車市場佔有率預測模型之研究」，長庚大學企業管理系碩士論文，2003。
14. 歐嘉瑞，「台灣地區汽車需求之研究」，國立交通大學運輸研究所博士論文，1995。
15. 鄭光清，「汽車電子資訊產品對車輛銷售之研究-傳統迴歸與模糊迴歸之預測比較」，大葉大學工業工程與科技管理學系碩士論文，2005。
16. 蕭志同 ，「台灣汽車製造業生產規模初探」，經濟情勢暨評論季刊第2卷第3期，1996。
17. 謝朋昇，「應用類神經網路於國產車銷售預測之研究」，大葉大學工業工程與科技管理學系碩士論文，2008。

相關網站
1. 中華民國統計資訊網
2. 台灣區車輛工業同業公會
3. 經濟部工業生產統計月報

英文部分
1. Abu-Eisheh, S. A. and Mannering, F., “Forecasting Automobile Demand for Economies in Transition, a Dynamic Simultaneous-Equation System Approach”, Transportation Planning and Technology, Vol. 25, No. 4, pp. 311-331, 2002.
2. Atsalakis, G. and Minoudaki, C., “Daily Irrigation Water Demand Prediction Using Adaptive Neuro-Fuzzy Inference System(ANFIS)”, International Conference on Energy, Environment, Ecosystems and Sustainable Development, pp. 369-374, 2007.
3. Banik, S., Chanchary, F. H., Rouf, R. A. and Khan K., “Modeling Chaotic Behavior of Dhaka Stock Market Index Values Using the Neuro-Fuzzy Model”, International Conference on Computer and Information Technology, pp. 1-6, 2007.
4. Bayus, B. L., “An Analysis of Product Lifetimes in a Technologically Dynamic Industry”, Management Science, Vol. 44, No. 6, pp. 763-775, 1998.
5. Box, G. E. P. and Jenkins, G. M., “Time Series Analysis Forecasting and Control”, 1st edition, San Francisco: Holden-Day, 1970.
6. Carlson, R. L. and Umble, M. M., “Statistical Demand Functions for Automobiles and Their Use for Forecasting in an Energy Crisis”, The Journal of Business, Vol.53, No. 2, pp. 193-204, 1980.
7. Firat, M. and Güngör, M., “Hydrological Time Series Modeling Using an Adaptive Neuro-Fuzzy Inference System”, Hydrological Processes, Vol.22, No. 13, pp. 2122-2132, 2008.
8. García, J. C. F. and Mendez, J. J. S., “A Comparison of ANFIS, ANN and DBR Systems on Volatile Time Series Identification”, Annual Conference of the North American Fuzzy Information Processing Society, pp. 319-324, 2007.
9. Jang, J. S. R., “ANFIS: Adaptive Network-Based Fuzzy Inference System”, IEEE Transactions on Systems, Man and Cybernetics, Vol. 23, No. 3, pp. 665-685, 1993.
10. Khashei, M., Bijari, M. and Ardali, G. A. R., “Improvement of Auto Regressive Integrated Moving Average Models using Fuzzy Logic and Artificial Neural Networks(ANNs)”, Neurocomputing, Vol. 72, No.4-6, pp. 956-967, 2009.
11. Levenhach, H. and Cleary, J. P., “Forecasting: Practice and Process for Demand Management”, Thomson, Duxbury, Belmont, 2006.
12. Lewis, C. D., “Industrial and Business Forecasting Methods”, London: Butterworths, 1982.
13. Nayak, P. C., Sudheer, K. P., Rangan, D. M. and Ramasastri, K. S., “A Neuro-Fuzzy Computing Technique for Modeling Hydrological Time Series”, Journal of Hydrology, Vol. 291, No. 1-2, pp. 52-66, 2004.
14. Romilly, P., Song, H. and Liu, X., “Modelling and Forecasting Car Ownership in Britain”, Transport Economics and Policy, Vol. 32, No. 2, pp. 165-185, 1998.
15. Rumelhart, D. E. and McClelland, J. L., “Parallel Distributed Processing : Explorations in the Microstructure of Cognition”, MIT Press, Cambridge, MA, Vol. 1, No. 1, pp. 547, 1986.
16. Sfetsos, A and Coonick, A. H., “Univariate and Multivariate Forecasting of Hourly Solar Radiation with Artificial Intelligence Techniques”, Solar Energy, Vol. 68, No. 2, pp. 169-178, 2000.
17. Takagi, T. and Sugeno, M., “Fuzzy Identification of Systems and Its Applications to Modeling and Control”, IEEE Transactions on Systems, Man, Cybernetics, Vol. 15, No. 1, pp. 116-132, 1985.
18. Tanner, C. F., “Long Term Forecasting of Vehicle Ownership and Road Traffic”, Journal of the Royal Statistical Society, Vol. 141, No. 1, pp. 14-63. 1978.
19. Valenzuela, O., Rojas, I., Rojas, F., Pomares, H., Herrera, L. J., Guillen, A., Marquez, L. and Pasadas, M., “Hybridization of Intelligent Techniques and ARIMA Models for Time Series Prediction”, Fuzzy Sets and Systems, Vol. 159, No. 7, pp. 821-845, 2008.
20. Wheelwright, S. C. and Makridakis, S., “Examination of the Use of Adaptive Filtering in Forecasting”, Operational Research Quarterly, Vol. 24, No.1, pp. 55-64, 1973.
21. Zhang, G. P., “Time Series Forecasting Using a Hybrid ARIMA and Neural Network Model”, Neurocomputing, Vol. 50, No. 1, pp. 159-175, 2003.