半導體廠商對未來景氣的判斷，從整體產業訂單出貨比的變動，最能具體反映。訂單出貨比是以未來設備訂單金額，除以現在實際付出的採購金額。訂單出貨比的預測在製造業、銷售業、高科技產業市場上以及財務經理和投資者的、財務經理跟投資者是個很重要的判斷景氣依據。雖然訂單出貨比在半導體市場變動上是個很重要的指標，卻很少研究能準確的預測訂單出貨比。為了發展一個有效預測出訂單出貨比的機制，這篇論文提出一個以基因演算法為基礎的最小二乘支持向量機方法。透過基因演算法的幫助，可以事先決定了的的支持向量機中最佳化的核函數函其他重要參數。在實驗中我們取1996年到2010年的訂單出貨比，根據目前半導體變動的資料去預測未來可能的訂單出貨比。訂單出貨比的變動或衰退造成的預測準確性差異也在文中去作討論。同時，實驗證明這篇提出的方法可以高達80% 以上的正確性在沒有嚴重的經濟衰減。在未來中，以基因演算法為基礎的最小二乘支持向量機可以運用在預測其他產業週期或趨勢上。

[1] G.E.P. Box, G.M. Jenkins, and G.C. Reinsel. Time series analysis: forecasting and control.
Holden-day San Francisco, 1970.
[2] M.J. Shaw and J.A. Gentry. Using an expert system with inductive learning to evaluate
business loans. Financial Management, 17(3):45–56, 1988.
[3] C.S. Park and I. Han. A case-based reasoning with the feature weights derived by analytic
hierarchy process for bankruptcy prediction. Expert Systems with Applications, 23(3):255–
264, 2002.
[4] P. Buta. Mining for financial knowledge with CBR. Ai Expert, 9(2):34–41, 1994.
[5] J.R. Coakley and C.E. Brown. Artificial neural networks in accounting and finance: Modeling
issues. Intelligent Systems in Accounting, Finance & Management, 9(2):119–144, 2000.
[6] G. Zhang, M.Y. Hu, Eddy Patuwo, and D.C. Indro. Artificial neural networks in bankruptcy
prediction: General framework and cross-validation analysis. European Journal of Opera-
tional Research, 116(1):16–32, 1999.
[7] G. Zhang and M.Y. Hu. Neural network forecasting of the British pound/US dollar exchange
rate. Omega, 26(4):495–506, 1998.
[8] I. Kaastra and M.S. Boyd. Forecasting futures trading volume using neural networks. Journal
of Futures Markets, 15(8):953–970, 1995.
[9] W.C. Chiang and G.W. Urban. A neural network approach to mutual fund net asset value
forecasting. Omega, 24(2):205–215, 1996.
[10] X.H. Yu. Can backpropagation error surface not have local minima. IEEE Transactions on
Neural Networks, 3(6):1019–1021, 1992.
[11] V. N. Vapnik. Statistical learning theory. Wiley, New York, 1998.
[12] F.E.H. Tay and L. Cao. Application of support vector machines in financial time series fore-
casting. Omega, 29(4):309–317, 2001.
[13] K. Kim. Financial time series forecasting using support vector machines. Neurocomputing,
55(1-2):307–319, 2003.
[14] J.H. Min and Y.C. Lee. Bankruptcy prediction using support vector machine with optimal
choice of kernel function parameters. Expert Systems with Applications, 28(4):603–614,
2005.
[15] S. Makridakis, S.C. Wheelwright, and R.J. Hyndman. Forecasting methods and applications.
Wiley-India, 2008.
[16] T.W. Anderson. An introduction to multivariate statistical analysis. JohnWiley & Sons New
York, 1984.
[17] N. Wiener. Nonlinear problems in random theory. 1966.
[18] J.G. De Gooijer Kuldeep. Some recent developments in non-linear time series modelling,
testing, and forecasting. International Journal of Forecasting, 8(2):135–156, 1992.
[19] W.E. Halal, M.D. Kull, and A. Leffmann. The George Washington University Forecast of
Emerging Technologies:: A Continuous Assessment of the Technology Revolution. Techno-
logical Forecasting and Social Change, 59(1):89–110, 1998.
[20] P.C. Chang, C.P. Wang, B.J.C. Yuan, and K.T. Chuang. Forecast of development trends in
Taiwan’s machinery industry. Technological Forecasting and Social Change, 69(8):781–802,
2002.
[21] P. Ronde. Delphi analysis of national specificities in selected innovative areas in Germany
and France. Technological Forecasting and Social Change, 70(5):419–448, 2003.
[22] R.R. Levary and D. Han. Choosing a technological forecasting method. INDUSTRIAL
MANAGEMENT-CHICAGO THEN ATLANTA-, 37:14–14, 1995.
[23] P. Young. Technological growth curves:: A competition of forecasting models. Technological
Forecasting and Social Change, 44(4):375–389, 1993.
[24] H. Ernst. The use of patent data for technological forecasting: the diffusion of CNC-
technology in the machine tool industry. Small Business Economics, 9(4):361–381, 1997.
[25] R.J. Watts and A.L. Porter. Innovation forecasting. Technological forecasting and social
change, 56(1):25–47, 1997.
[26] N. Meade and T. Islam. Technological forecasting–model selection, model stability, and
combining models. Management Science, 44(8):1115–1130, 1998.
[27] L.D. Frank. An analysis of the effect of the economic situation on modeling and forecasting
the diffusion of wireless communications in Finland. Technological forecasting and social
change, 71(4):391–403, 2004.
[28] R.L. Hirsch. Reorienting an industrial research laboratory. Research Management, 29(1):26–
30, 1986.
[29] D.N. Fuller, W.T. Scherer, and T.A. Pomroy. An exploration and case study of population
classification for managed healthcare within a state-based modelling framework. Interna-
tional Journal of Healthcare Technology and Management, 5(1):123–140, 2003.
[30] C. Hjelkrem. Forecasting with limited information: A study of the Norwegian ISDN access
market. JOURNAL OF BUSINESS FORECASTING METHODS AND SYSTEMS, 20(3):18–
24, 2001.
[31] M. Kohlbeck. Reporting Earnings at Summer Technology–A Capstone Case Involving Inter-
mediate Accounting Topics. Issues in accounting education, (2):195–212, 2005.
[32] K. Hornik Maxwell and H. White. Multilayer feedforward networks are universal approxi-
mators. Neural networks, 2(5):359–366, 1989.
[33] H. Raman and N. Sunilkumar. Multivariate modelling of water resources time series using
artificial neural networks/Mod□lisation multivari□e de s□ries chronologiques hydrologiques
gr□ce □ l’utilisation de r□seaux neuronaux artificiels. Hydrological Sciences Journal,
40(2):145–163, 1995.
[34] A. Elshorbagy, S.P. Simonovic, and U.S. Panu. Performance evaluation of artificial neural
networks for runoff prediction. Journal of Hydrologic Engineering, 5:424, 2000.
[35] G. Zhang, B. Eddy Patuwo, and M.U. Hu. Forecasting with artificial neural networks: The
state of the art. International journal of forecasting, 14(1):35–62, 1998.
[36] K. Hsu, H.V. Gupta, and S. Sorooshian. Artificial neural network modeling of the rainfall-
runoff process. Water resources research, 31(10):2517–2530, 1995.
[37] G.P. Zhang, B.E. Patuwo, and M.Y. Hu. A simulation study of artificial neural networks for
nonlinear time-series forecasting. Computers & Operations Research, 28(4):381–396, 2001.
[38] T.S. Quah and B. Srinivasan. Improving returns on stock investment through neural network
selection. Expert Systems with Applications, 17(4):295–301, 1999.
[39] K. Kim and I. Han. Genetic algorithms approach to feature discretization in artificial neu-
ral networks for the prediction of stock price index. Expert Systems with Applications,
19(2):125–132, 2000.
[40] S. Lawrence, C.L. Giles, and A.C. Tsoi. Lessons in neural network training: Overfitting may
be harder than expected. In Proceedings of the National Conference on Artificial Intelligence,
pages 540–545. Citeseer, 1997.
[41] T.B. Trafalis and H. Ince. Support vector machine for regression and applications to finan-
cialforecasting. In Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Neural Networks, 2000. IJCNN 2000, volume 6, 2000.
[42] F.E.H. Tay and L.J. Cao. Improved financial time series forecasting by combining support
vector machines with self-organizing feature map. Intelligent Data Analysis, 5(4):339–354,
2001.
[43] F.E.H. Tay and LJ Cao. Modified support vector machines in financial time series forecasting.
Neurocomputing, 48(1-4):847–861, 2002.
[44] F.E.H. Tay and L.J. Cao. e-descending support vector machines for financial time series
forecasting. Neural Processing Letters (Netherlands), 15(2):179–195, 2002.
[45] L.J. Cao and F.E.H. Tay. Support vector machine with adaptive parameters in financial time
series forecasting. IEEE Transactions on neural networks, 14(6):1506–1518, 2003.
[46] T. Van Gestel, J.A.K. Suykens, D.E. Baestaens, A. Lambrechts, G. Lanckriet, B. Vandaele,
B. De Moor, and J. Vandewalle. Financial time series prediction using least squares support
vector machines within the evidence framework. IEEE Transactions on Neural Networks,
12(4):809, 2001.
[47] D.K. Wedding and Cios K.J. Time series forecasting by combining RBF networks, certainty
factors, and the Box-Jenkins model. Neurocomputing, 10(2):149–168, 1996.
[48] J.T. Luxhu˛j, J.O. Riis, and B. Stensballe. A hybrid econometric–neural network modeling
approach for sales forecasting. International Journal of Production Economics, 43(2-3):175–
192, 1996.
[49] I. Ginzburg and D. Horn. Combined neural networks for time series analysis. Advances in
Neural Information Processing Systems, pages 224–224, 1994.
[50] Y. Liang and Y. Sun. An improved method of support vector machine and its applications to
financial time series forecasting. Progress in Natural Science, 13(9):696–700, 2003.
[51] T. Chen and Y.C. Wang. A hybrid fuzzy and neural approach for forecasting the book-to-bill
ratio in the semiconductor manufacturing industry. The International Journal of Advanced
Manufacturing Technology, pages 1–13.
[52] H.K. Chow and K.M. Choy. Forecasting the global electronics cycle with leading indicators:
A Bayesian VAR approach. International Journal of Forecasting, 22(2):301–315, 2006.
[53] C.M. Bishop. Neural networks for pattern recognition. Oxford University Press, USA, 1995.
[54] S. Haykin. Neural networks: a comprehensive foundation. 1999. Upper Saddle River, New
Jersey.
[55] J.J. Huang, G.H. Tzeng, and C.S. Ong. Two-stage genetic programming (2SGP) for the credit
scoring model. Applied Mathematics and Computation, 174(2):1039–1053, 2006.
[56] S. Haykin. Neural networks: a comprehensive foundation. Prentice Hall PTR Upper Saddle
River, NJ, USA, 1994.
[57] V.S. Desai, J.N. Crook, G.A. Overstreet, and A. George. A comparison of neural networks
and linear scoring models in the credit union environment. European Journal of Operational
Research, 95(1):24–37, 1996.
[58] R. Malhotra and DK Malhotra. Evaluating consumer loans using neural networks. Omega,
31(2):83–96, 2003.
[59] S. Piramuthu. Financial credit-risk evaluation with neural and neurofuzzy systems. European
Journal of Operational Research, 112(2):310–321, 1999.
[60] H.L. Jensen. Using neural networks for credit scoring. Managerial Finance, 18(6):15–26,
1993.
[61] V.S. DESAI, D.G. Conway, J.N. CROOK, and G.A. OVERSTREET. Credit-scoring models
in the credit-union environment using neural networks and genetic algorithms. IMA Journal
of Management Mathematics, 8(4):323, 1997.
[62] R. F□raud and F. Cl□rot. A methodology to explain neural network classification. Neural
Networks, 15(2):237–246, 2002.
[63] R. Nath, B. Rajagopalan, and R. Ryker. Determining the saliency of input variables in neural
network classifiers. Computers & Operations Research, 24(8):767–773, 1997.
[64] B.E. Boser, I.M. Guyon, and V.N. Vapnik. A training algorithm for optimal margin classifiers.
In Proceedings of the fifth annual workshop on Computational learning theory, pages 144–
152. ACM, 1992.
[65] J.A.K. Suykens and J. Vandewalle. Least squares support vector machine classifiers. Neural
processing letters, 9(3):293–300, 1999.
[66] D. Tsujinishi and S. Abe. Fuzzy least squares support vector machines for multiclass prob-
lems. Neural Networks, 16(5-6):785–792, 2003.
[67] J.A.K. Suykens, J. De Brabanter, L. Lukas, and J. Vandewalle. Weighted least squares support
vector machines: robustness and sparse approximation* 1. Neurocomputing, 48(1-4):85–105,
2002.
[68] S. Zheng, J. Tian, J. Liu, and C. Xiong. Novel algorithm for image interpolation. Optical
Engineering, 43:856, 2004.
[69] C.H.Wu, G.H. Tzeng, Y.J. Goo, andW.C. Fang. A real-valued genetic algorithm to optimize
the parameters of support vector machine for predicting bankruptcy. Expert Systems with
Applications, 32(2):397–408, 2007.
[70] P.T. Lin. Support vector regression: Systematic design and performance analysis. Unpub-
lished Doctoral Dissertation, Department of Electronic Engineering, National Taiwan Uni-
versity, 2001.
[71] M. Zbigniew. Genetic algorithms+ data structures= evolution programs. third extended re-
vised edition, Springer Verlag heidenberg New York, 1999.
[72] J. Boudoukh, M. Richardson, and R. Whitelaw. The best of both worlds. Risk, 11(5):64–67,
1998.
[73] A.A. Adewuya. New methods in genetic search with real-valued chromosomes. 1996.
[74] C.Y. Huang, G.H. Tzeng, C.C. Chan, and H.C. Wu. Semiconductor Market Fluctuation Indi-
cators and Rules Derivations by using the Rough Set Theory.
[75] G.R. Fong. State strength, industry structure, and industrial policy: American and Japanese
experiences in microelectronics. Comparative Politics, 22(3):273–299, 1990.
[76] W.H. Liu. Determinants of the semiconductor industry cycles. Journal of Policy Modeling,
27(7):853–866, 2005.
[77] A. Allan. Business cycle market/demand forecasts vs. TSCR cycle model. In International
SEMATECH. Presentation at the global economic workshop, Monterey, California, USA,
2001.
[78] R. Leckie. The semiconductor cyclea˛XHere we go again, 2001.
[79] B. McClean, B. Matas, and T. Yancey. The McClean Report: 2001 Edition. IC Insights,
2001.
[80] C. Terwiesch, Z.J. Ren, T.H. Ho, and M.A. Cohen. An empirical analysis of forecast sharing
in the semiconductor equipment supply chain. Management Science, 51(2):208–220, 2005.
[81] H.L. Lee, V. Padmanabhan, and S. Whang. Information distortion in a supply chain: the
bullwhip effect. Management science, 43(4):546–558, 1997.
[82] U. Chandra, A. Oricassini, and G. Waymire. The information content of non-financial dis-
closures: evidence from the semiconductor industrya˛zs book-to-bill ratio. Technical report,
Working Paper, Emero University, 1997.
[83] A.J.W. van de Gevel. From confrontation to coopetition in the globalized semiconductor
industry. 2000.
[84] B. McClean, B. Matas, and T. Yancey. The McClean Report: 2005 Edition. IC Insights,
2005.
[85] S. Dawley. Fluctuating rounds of inward investment in peripheral regions: semiconductors
in the North East of England. Economic Geography, 83(1):51–73, 2007.
5