Neural Computing and Applications

, Volume 20, Issue 8, pp 1193–1203 | Cite as

Correlation-aided support vector regression for forex time series prediction

ISNN 2010

Abstract

Market is often found behaving surprisingly similar to history, which implies that correlation exists significant for market trend analysis. In the context of Forex market analysis, this paper proposes a correlation-aided support vector regression (cSVR) for time series application, where correlation data are extracted through a graphical channel correlation analysis, compensated by a parameterized Pearson’s correlation to exclude noise meanwhile minimize useful information lost. The effectiveness of cSVR against SVR is confirmed by experiments on 5 contracts (NZD/AUD, NZD/EUD, NZD/GBP, NZD/JPY, and NZD/USD) exchange rate prediction within the period from January 2007 to December 2008.

Keywords

Support vector regression Graphical channel correlation Pearson’s correlation Forex time series prediction 

References

  1. 1.
    Kirkpatrick CD, Dahlquist JR (2006) Technical analysis: the complete resource for financial market technicians. Financial Times 704Google Scholar
  2. 2.
    Abarbanell JS, Bushee BJ (1997) Fundamental analysis, future earnings, and stock prices. J Account Res 35(1):1–24 [Online]. Available: http://www.jstor.org/stable/2491464 Google Scholar
  3. 3.
    Taylor MP, Allen H (1992) The use of technical analysis in the foreign exchange market. J Int Money Finance 11(3):304–314CrossRefGoogle Scholar
  4. 4.
    Park C, Irwin S (2004) The profitability of technical analysis: a review. AgMAS, Tech Rep, vol 4Google Scholar
  5. 5.
    Murphy JJ (1999) Technical analysis of the financial markets. New York Institute of Finance, p 264Google Scholar
  6. 6.
    Schwager JD (1996) Technical analysis. Wiley, New Jersey, p 545Google Scholar
  7. 7.
    Saacke P (2002) Technical analysis and the effectiveness of central bank intervention. J Int Money Finance 21(4):459– 479, [Online]. Available: http://www.sciencedirect.com/science/article/B6V9S-45BCP6T-5/2/6e35493047aec373a8f6612d2e4071cf Google Scholar
  8. 8.
    Neely CJ (1997) Technical analysis in the foreign exchange market: a layman’s guide. Review no. Sep, pp 23–38Google Scholar
  9. 9.
    Appel G (2005) Technical analysis: power tools for active investors. FT Press, Upper Saddle RiverGoogle Scholar
  10. 10.
    DSouza C (2002) A market microstructure analysis of foreign exchange intervention in canada. Bank of Canada Working Paper 2002–16, vol 1192–5434Google Scholar
  11. 11.
    Lui Y-H, Mole D (1998) The use of fundamental and technical analyses by foreign exchange dealers: Hong kong evidence. J Int Money Finance 17(3):535–545 [Online]. Available: http://www.sciencedirect.com/science/article/B6V9S-3V5WNPP-10/2/9f85ed3465b1c7b757fb453c46c97531 Google Scholar
  12. 12.
    Chou Y-l (1975) Statistical analysis. Holt International, New YorkGoogle Scholar
  13. 13.
    Rodgers JL, Nicewander WA (1988) Thirteen ways to look at the correlation coefficient. Am Stat 42(1):59–66CrossRefGoogle Scholar
  14. 14.
    Pearson K (1897) Mathematical contributions to the theory of evolution–on a form of spurious correlation which may arise when indices are used in the measurement of organs. The Royal Society, pp 489–498Google Scholar
  15. 15.
    Corder G, Foreman D (2009) Nonparametric statistics for non-statisticians: a step-by-step approach. Wiley, New JerseyCrossRefGoogle Scholar
  16. 16.
    Kondratenko VV, Kuperin YA (2003) Using recurrent neural networks to forecasting of forex, [Online]. Available: http://www.citebase.org/abstract?id=oai:arXiv.org:cond-mat/0304469
  17. 17.
    Kwapien J, Gworek S, Drozdz S (2009) Structure and evolution of the foreign exchange networks. Acta Phys Pol B 40:175 [Online]. Available: http://www.citebase.org/abstract?id=oai:arXiv.org:0901.4793 Google Scholar
  18. 18.
    Plackett RL (1983) Karl pearson and the chi-squared test. Int Stat Rev 51(1):59C72MathSciNetGoogle Scholar
  19. 19.
    Tate RF (1954) Correlation between a discrete and a continuous variable. point-biserial correlation. Ann Math Stat 25(3):603–607MathSciNetCrossRefGoogle Scholar
  20. 20.
    Myers JL, Well A (2003) Research design and statistical analysis, 2 edn. Lawrence Erlbaum, MahwahGoogle Scholar
  21. 21.
    Detsky AS, Mclaughlin JR, Baker JP, Johnston N, Whittaker S, Mendelson RA, Jeejeebhoy KN (1987) What is subjective global assessment of nutritional status? Parenter Enteral Nutr 11(1):8–13CrossRefGoogle Scholar
  22. 22.
    Mantel N (1963) Chi-square tests with one degree of freedom; extensions of the mantel- haenszel procedure. J Am Stat Assoc 58(303):690–700MathSciNetCrossRefGoogle Scholar
  23. 23.
    Paez JG, J?nne PA, Lee JC, Tracy S, Greulich H, Gabriel S, Herman P, Kaye FJ, Lindeman N, Boggon TJ, Naoki K, Sasaki H, Fujii Y, Eck MJ, Sellers WR, Johnson BE, Meyerson M (2004) Egfr mutations in lung cancer: correlation with clinical response to gefitinib therapy. Sci Exp 304(5676):1497–1500Google Scholar
  24. 24.
    Yu C, Chan Y, Zhang Q, Yip G, Chan C, Kum L, Wu L, Lee A, Lam Y, Fung J (2005) Benefits of cardiac resynchronization therapy for heart failure patients with narrow qrs complexes and coexisting systolic asynchrony by echocardiography. Am Coll Cardiol 48(11):2251–2257CrossRefGoogle Scholar
  25. 25.
    Wray D (2004) Literacy: major themes in education. In: Major themes in education. Routledge Falmer, University of Warwick, England. ISBN 978041527709Google Scholar
  26. 26.
    Akdede BBK, Alptekin K, Kitis A, Arkar H, Akvardar Y (2005) Effects of quetiapine on cognitive functions in schizophrenia. Prog Neuropsychopharmacol Biol Psychiatry 29(2):233–238CrossRefGoogle Scholar
  27. 27.
    Deberard MS, Spielmans GI, Julka DL (2004) Predictors of academic achievement and retention among college freshmen: a longitudinal study. Coll Stud J 38(1):66–80Google Scholar
  28. 28.
    Gelfand J, Feldman S, Stern R, Thomas J, Rolstad T, Margolis D (2004) Determinants of quality of life in patients with psoriasis: a study from the us population. Am Acad Dermatol 51(5):704–708CrossRefGoogle Scholar
  29. 29.
    Sutherland E, Martin R, Bowler R, Zhang Y, Rex M, Kraft M (2004) Physiologic correlates of distal lung inflammation in asthma. Allerg Clin Immunol 113(6):1046–1050CrossRefGoogle Scholar
  30. 30.
    Boot RG, Verhoek M, Fost Md, Hollak CEM, Maas M, Bleijlevens B, Breemen MJv, Meurs Mv, Boven LA, Laman JD, Moran MT, Cox TM, Aerts JMFG (2004) Marked elevation of the chemokine ccl18/parc in gaucher disease: a novel surrogate marker for assessing therapeutic intervention. Blood 103(1):33–39CrossRefGoogle Scholar
  31. 31.
    Panackal AA, Gribskov JL, Staab JF, Kirby KA, Rinaldi M, Marr KA (2006) Clinical significance of azole antifungal drug cross-resistance in candida glabrata. Clin Microbiol 44(5):1740–1743CrossRefGoogle Scholar
  32. 32.
    Wong KF, Selzer T, Benkovic SJ, Hammes-Schiffer S (2005) Impact of distal mutations on the network of coupled motions correlated to hydride transfer in dihydrofolate reductase. Natl Acad Sci USA 102(19):6807–6812Google Scholar
  33. 33.
    Lapata M (2006) Automatic evaluation of information ordering: Kendall’s tau. Comput Linguist 32(4):471–484CrossRefGoogle Scholar
  34. 34.
    Hilde CB, Havard H (2006) The importance of interest rates for forecasting the exchange rate. J Forecast 25(3):209–221. doi:10.1002/for.983 MathSciNetCrossRefGoogle Scholar
  35. 35.
    Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999CrossRefGoogle Scholar
  36. 36.
    Drucker H, Burges CJC, Kaufman L, Smola A, Vapnik V (1997) Support vector regression machines. Adv Neural Inf Process Syst (9):115–161Google Scholar
  37. 37.
    Scholkopf B, Burges CJC, Smola AJ (1999) Advances in Kernel methods–support vector learning. The MIT Press, CambridgeGoogle Scholar
  38. 38.
    Sapankevych NI, Sankar R (2009) Time series prediction using support vector machines: a survey. IEEE Comput Intell 4(2):25–37Google Scholar
  39. 39.
    Cheng J, Randall A, Baldi P (2006) Prediction of protein stability changes for single-site mutations using support vector machines. Proteins Struct Funct Bioinform 62(4):1125–1132CrossRefGoogle Scholar
  40. 40.
    Trafalis TB, Ince H (2000) Support vector machine for regression and applications to financial forecasting, pp 348–353Google Scholar
  41. 41.
    Tay FEH, Cao LJ (2001) Application of support vector machines in financial time series forecasting. Omega 29:209–317CrossRefGoogle Scholar
  42. 42.
    Tay FEH, CaO LJ (2002) Modified support vector machines in financial time series forecasting. Neurocomputing 48(1-4):847–861CrossRefGoogle Scholar
  43. 43.
    Van Gestel EA (2001) Tony Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Trans Neural Netw 12(4):809–821CrossRefGoogle Scholar
  44. 44.
    Cao L and Gu Q (2002) Dynamic support vector machines for non-stationary time series forecasting. Intell Data Anal 6(1):67–83Google Scholar
  45. 45.
    Lu C-J, Lee T-S, Chiu C-C (2009) Financial time series forecasting using independent component analysis and support vector regression. Decision Support Syst 47(2):115–125 [Online]. Available: http://www.sciencedirect.com/science/article/B6V8S-4VKXBVX-1/2/299b01b62df0f035ab42062e6ad2c22c
  46. 46.
    Huang C-L, Tsai C-Y (2009) A hybrid sofm-svr with a filter-based feature selection for stock market forecasting. Expert Syst Appl 36(2), Part 1, pp 1529–1539 [Online]. Available: http://www.sciencedirect.com/science/article/B6V03-4RC2NKB-4/2/3d8820b4b07243e5914630647d8492e8
  47. 47.
    Cao L (2003) Support vector machines experts for time series forecasting. Neurocomputing 51:321–339CrossRefGoogle Scholar
  48. 48.
    Cao LJ, Tay FEH (2003) Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans Neural Netw 14(6):1506–1518CrossRefGoogle Scholar
  49. 49.
    Cao L, Tay FEH (2001) Financial forecasting using support vector machines. Neural Comput Appl 10(2):184–192CrossRefGoogle Scholar
  50. 50.
    Min JH, Lee Y-C (2005) Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert Syst Appl 28(4):603–614CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2010

Authors and Affiliations

  1. 1.Auckland University of TechnologyAucklandNew Zealand

Personalised recommendations