Sensitivity and Generalization of SVM with Weighted and Reduced Features

  • Yan-xing Hu
  • James N. K. Liu
  • Li-wei Jia
Conference paper


Support Vector Machine, as a modern statistical learning method based on the principle of structure risk minimization rather than the empirical risk minimization, has been widely applied to the small-sample, non-linear and high-dimensional problems. Many new versions of SVM have been proposed to improve the performance SVM. Some of the new versions focus on processing the features of SVM. For example, give the features weight values or reduce some unnecessary features. A new feature weighted SVM and a feature reduced SVM are proposed in this chapter. The two versions of SVM are applied to the regression works to predict the price of a certain stock, and the outputs are compared with classical SVM. The results showed that the proposed feature weighted SVM can improve the accuracy of the regression, and the proposed featured reduced SVM is sensitive to the data sample for testing


Support Vector Machine Stock Price Support Vector Regression Classical Support Vector Machine Decision Table 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bao, Y. K., Lu, Y. S., Zhang, J. L.: Forecasting stock price by SVMs regression artificial intelligence. Lecture Notes in Comput. Sci. 319, 2295-303 (2004)Google Scholar
  2. 2.
    Cai, R. C., Hao, Z. F., Wen, W., Han, H.: Kernel based gene expression pattern discovery and its application on cancer classification. Neurocomputing. 73(13-15), 2562-2570 (2010)CrossRefGoogle Scholar
  3. 3.
    Chen, P. J., Wang, G. Y., Yang, Y., Zhou, J.: Facial expression recognition based on rough set theory andsVM. Lecture Notes in Comput. Sci. 4062, 772-777 (2006)CrossRefGoogle Scholar
  4. 4.
    Cristianini, N., Taylor, J. S.: An introduction to support vector machines. Cambridge University Press. Cambridge, UK(2000)Google Scholar
  5. 5.
    Chen, Y. W., Lin, C. J.: Combining SVMs with various feature selection strategies. Stud. Fuzziness Soft Comput. 207, 315-324 (2006)CrossRefGoogle Scholar
  6. 6.
    Deng, J. L.: Introduction to Grey system theory. J. Gre. Syst. 1(1), 103-104 (1989)MATHGoogle Scholar
  7. 7.
    Dong, H., Fu, H. L., Leng, W. M.: Support vector machines for time series regression and prediction, J. Syst. Sim. 18 (7), 1784-1788 (2006)Google Scholar
  8. 8.
    Huang, Y. M., Du, S. X.: Weighted support vector machine for classification with uneven training class sizes. Mach. Learn. and. Cyb. 7, 4365 - 4369 (2005)Google Scholar
  9. 9.
    Jian, L. R.: The Uncertain Decision Making Oriented Rough Set Method and The Application. Science publish hall, Beijing (2008)Google Scholar
  10. 10.
    Jiang, X. F., Zhang, Y., Lv, J.C.: Fuzzy SVM with a new fuzzy membership function, Neural. Comput. And. Appl. 15, 268-276 (2006)CrossRefGoogle Scholar
  11. 11.
    Research on support vector regression machine based on weighted feature. Comp. Eng. And. Appl. 43(6), 42-44 (2007)Google Scholar
  12. 12.
    LeBaron, B.: Nonlinear dynamics and stock returns. J. Bus. 62(3), 311-337 (1989)CrossRefGoogle Scholar
  13. 13.
    Li, Y., Gong, S., Sherrah, J.: Support vector machine based multi-view face detection and recognition. Image Vis. Comput. 22(5), 413-427 (2004)CrossRefGoogle Scholar
  14. 14.
    Lingras, P., Butz, C.: Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification. Inf. Sci. 177(18), 3782-3798 (2007)CrossRefGoogle Scholar
  15. 15.
    Liu, S. F., Lin, Y.: Introduction to Grey Systems Theory. Unds. Comp. Sys. 68, 1-18 (2011)Google Scholar
  16. 16.
    Lu, C. J., Lee, T. S.: Financial time series forecasting using independent component analysis and support vector regression. Decision. Supp. Syst. 47(2), 115-125 (2009)CrossRefGoogle Scholar
  17. 17.
    Makridakis, S., Winkler, R. L.: Sampling distribution of post sample forecasting errors. Appl.Stat. 38,331-342 (1989)MATHCrossRefGoogle Scholar
  18. 18.
    Miao, D. Q.: Rough Set Theory Algorithms and Applications. Tinghua University publish, Beijng (2008)Google Scholar
  19. 19.
    Pai, P. F., Lin, C. S.: A hybrid ARIMA and support vector machines model in stock price forecasting. Omega. 33(6), 497-505 (2005)CrossRefGoogle Scholar
  20. 20.
    Pal, M., Foody, G. M.: Feature Selection for classification of hyperspectral data by SVM. IEEE Trans. Geos. Rem. 48(5), 2297 - 2307 (2010)CrossRefGoogle Scholar
  21. 21.
    Pawlak, Z.: Rough sets, Int. J. Comput. And. Inf. Sci. 11(5), 341-356 (1982)MathSciNetMATHCrossRefGoogle Scholar
  22. 22.
    Scholkopf, B., Smola, A. J.: Statistical Learning and Kernel Methods. MIT Press, Cambridge, MA (2000)Google Scholar
  23. 23.
    Slowron, A., Rauszer, C.: The discernibility matrices and function in information systems. In: SlowinskiR. (1st.) Handbook of Applications and Advance of Rough Sets Theory, pp. 331-362. Kluwer Academic Publishers, Dordrecht (1992)Google Scholar
  24. 24.
    Stitson, M. O.,Weston, J. A. E., Gammerman, A., Vovk, V., Vapnik, V. N.: Theory of Support Vector Machines, Royal Holloway Technical Report, CSD-TR-96-17 (1996)Google Scholar
  25. 25.
    Tang, L. B., Huan, Y. S., Ling, X. T.: GARCH prediction using spline wavelet support vector machine machines. Neural. Comput. Appl. 18(8), 913-917 (2009)CrossRefGoogle Scholar
  26. 26.
    Tang, Y. Q., Mao, J. J.: China’s power supply SVM regression forecast based on rough Set attribute reduction. Comput. Tec. And. Dev. 20(9), 48-52 (2010)Google Scholar
  27. 27.
    Vapnik, V. N.: An overview of an overview of statistical learning theory. IEEE.Tran.Neur.Net, 10(5), 988-999 (1999)Google Scholar
  28. 28.
    Vapnik, V. N.: Statistical Learning Theory. Wiley, NewYork (1998)MATHGoogle Scholar
  29. 29.
    Vapnik, V. N.: The Nature of Statistical Learning Theory. Springer, NewYork (1995)MATHGoogle Scholar
  30. 30.
    Wang, X. Z., He, Q.: Enhancing Generalization capability of SVM classifiers with feature weight adjustment. Lecture Notes in Comput. Sci. 3213, 1037-1043 (2004)CrossRefGoogle Scholar
  31. 31.
    Yang, H. Q., Chan, L. W., King, I.: Support vector machine regression for volatile stock market prediction. Lecture Notes in Comput. Sci. 2412, 143-152 (2002)Google Scholar
  32. 32.
    Yeh, C. H.: A multiple-kernel support vector regression approach for stock market price forecasting. Exp. Syst. Appl. 38(3), 2177-2186 (2011)CrossRefGoogle Scholar
  33. 33.
    Yeung, Daniel S., Wang, D. F., Ng, W. Y., Tsang, Eric. C. C., Wang, X. Z.: Structured large margin machines: sensitive to data distributions. Mach.Learn. 68(2), 171-200 (2007)Google Scholar
  34. 34.
    Ziarko, W.: Variable precision rough set model. J. Comput. Syst. Sci. 46(1), 39-59 (1993)MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Department of ComputingThe Hong Kong Polytechnic UniversityHong KongChina
  2. 2.Software Engineering School of Xi’an Jiaotong UniversityXi’anChina

Personalised recommendations