Skip to main content
SpringerLink
Log in

CARTMAP: a neural network method for automated feature selection in financial time series forecasting

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In the past two decades, there has been much interest in applying neural networks to financial time series forecasting. Yet, there has been relatively little attention paid to selecting the input features for training these networks. This paper presents a novel CARTMAP neural network based on Adaptive Resonance Theory that incorporates automatic, intuitive, transparent, and parsimonious feature selection with fast learning. On average, over three separate 4-year simulations spanning 2004–2009 of Dow Jones Industrial Average stocks, CARTMAP outperformed related and classical alternatives. The alternatives were an industry standard random walk, a regression model, a general purpose ARTMAP, and ARTMAP with stepwise feature selection. This paper also discusses why the novel feature selection scheme outperforms the alternatives and how it can represent a step toward more transparency in financial modeling.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Amis G, Carpenter G (2007) Default ARTMAP 2. In: Proceedings of the international joint conference on neural networks (IJCNN, 07), Orlando, Florida, pp 777–782

  2. Aragones E, Gilboa I, Postlewaite A, Schmeidler D (2005) Fact-free learning. Am Econ Rev 95:1355–1368

    Article  Google Scholar 

  3. Bishop C (2006) Pattern recognition and machine learning. Springer, New York

    MATH  Google Scholar 

  4. Blalock HM Jr (1963) Correlated independent variables: the problem of multicollinearity. Soc Forces, University of North Carolina Press

  5. Bodyanskiy Y, Popov S (2006) Neural network approach to forecasting quasiperiodic financial time series. Eur J Oper Res 175:1357–1366

    Article  MathSciNet  MATH  Google Scholar 

  6. Brockett P, Golden L, Jang J, Yang C (2006) A comparison of neural network, statistical methods, and variable choice for life insurers’ financial distress prediction. J Risk Insur 73(3):397–419

    Article  Google Scholar 

  7. Carpenter G, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comput Vis Graph Image Process 37(54):115

    Google Scholar 

  8. Carpenter G, Grossberg S, Reynolds J (1991) ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network. Neural Netw 4:565–588

    Article  Google Scholar 

  9. Carpenter G, Grossberg S, Rosen D (1991) Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Netw 4:759–771

    Article  Google Scholar 

  10. Chao L, Knight R (1998) Contribution of human prefrontal cortex to delay performance. J Cogn Neurosci 10:167–177

    Article  Google Scholar 

  11. Chartered Financial Analyst Institute (2010) CFA program curriculum. CFA Institute, Pearson

    Google Scholar 

  12. Chen W, Shih J (2006) Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets. Int J Electron Finance 1(1):49–67

    Google Scholar 

  13. Chen W, Shih J, Wu S (2006) Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets. Int J Electron Finance 1(1):49–67

    Google Scholar 

  14. Conway A, Cowan N, Bunting M (2001) The cocktail party phenomenon revisited: the importance of working memory capacity. Psychon Bull Rev 8:331–335

    Article  Google Scholar 

  15. Duda R, Hart P, Stork D (2001) Pattern classification. Wiley-Interscience, New York

    MATH  Google Scholar 

  16. Fama E (1970) Efficient capital markets: a review of theory and empirical work. J Finance 25(2):383–417

    Article  Google Scholar 

  17. Hamilton J (1994) Time series analysis. Princeton University Press, Princeton

    MATH  Google Scholar 

  18. Higgins J (2004) Introduction to modern nonparametric statistics. Brooks/Cole-Thomson Learning, Pacific Grove

    Google Scholar 

  19. Kaastra I, Boyd M (1996) Designing a neural network for forecasting financial time series. Neurocomputing 10:215–236

    Article  Google Scholar 

  20. Kane M, Engle R (2002) The role of prefrontal cortex in working-memory capacity, executive attention, and general fluid intelligence: an individual-differences perspective. Psychon Bull Rev 9(4):637–671

    Article  Google Scholar 

  21. Kim K (2006) Artificial neural networks with evolutionary instance selection for financial forecasting. Expert Syst Appl 30:519–526

    Article  Google Scholar 

  22. Kim K, Han I (2000) Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Syst Appl 19(2):125–132

    Article  MathSciNet  Google Scholar 

  23. Kirkos E, Spathis C, Manolopoulos Y (2007) Data mining techniques for the detection of fraudulent financial statements. Expert Syst Appl 32:995–1003

    Article  Google Scholar 

  24. Kirkpatrick C, Dahlquist J (2006) Technical analysis: the complete resource for financial market technicians. FT Press, Upper Saddle River

    Google Scholar 

  25. Kumar K, Bhattacharya S (2006) Artificial neural network vs linear discriminant analysis in credit ratings forecast. Rev Account Finance 5(3):216–227

    Article  Google Scholar 

  26. Kwon Y, Moon B (2007) A hybrid neurogenetic approach for stock forecasting. IEEE Trans Neural Netw 18(3):851–864

    Article  MathSciNet  Google Scholar 

  27. Leung C, Tsoi A (2005) Combined learning and pruning for recurrent radial basis function networks based on recursive least square algorithms. Neural Comput Appl 15:62–78

    Google Scholar 

  28. Lina C, Huang J, Gena M, Tzeng G (2006) Recurrent neural network for dynamic portfolio selection. Appl Math Comput 175(2):1139–1146

    Article  MathSciNet  Google Scholar 

  29. Lintner J (1965) The valuation of risk assets and selection of risky investments in stock portfolios and capital budgets. Rev Econ Stat 47:13–37

    Article  Google Scholar 

  30. Liu B, Cui Q, Jiang T, Ma S (2004) A combinational feature selection and ensemble neural network method for classification of gene expression data. BMC Bioinform 5:136. doi:10.1186/1471-2105-5-136

    Article  Google Scholar 

  31. Lo A (2001) Bubble, rubble, finance in trouble? J Psychol Financial Mark 3:76–86

    Article  Google Scholar 

  32. Lo A (2007) The efficient markets hypothesis. In: Blume L, Durlauf S (eds) The new Palgrave dictionary of economics. Palgrave Macmillan, New York

  33. Lo A, Repin D (2002) The psychophysiology of real-time financial risk processing. J Cogn Neurosci 14(3):323–339

    Article  Google Scholar 

  34. Loeb G (1996) The battle for investment survival. Wiley, Malden

    Google Scholar 

  35. Malkiel B (1973) A random walk down Wall Street. W. W. Norton & Company, New York

    Google Scholar 

  36. Markowitz H (1952) The utility of wealth. J Political Econ 2:151–158

    Google Scholar 

  37. McQueen G, Thorley S (1999) Mining fool’s gold. Financial Analysts J 55(2):61–72

    Article  Google Scholar 

  38. Miller P, Seier W (1994) Strategy utilization deficiencies in children: when, where, and why. In: Reese H (ed) Advances in child development and behavior, vol 25. Academic Press, Salt Lake City

  39. Murphy J (1999) Technical analysis of the financial markets: a comprehensive guide to trading methods and applications. New York Institute of Finance, New York

    Google Scholar 

  40. Parsons O, Carpenter G (2003) ARTMAP neural networks for information fusion and data mining: map production and target recognition methodologies. Neural Netw 16:1075–1089

    Article  Google Scholar 

  41. Posner M, Rothbart M, Thomas-Thrapp L, Gerardi G (1998) Development of orienting to locations and objects. In: Wright R (ed) Visual attention. Oxford University Press, New York

  42. Schwager J (1995) The new market wizards: conversations with America’s top traders. Wiley, Hoboken

    Google Scholar 

  43. Sharpe W (1965) Capital asset prices: a theory of market equilibrium under conditions of risk. J Finance 19(3):425–442

    MathSciNet  Google Scholar 

  44. Sharpe W (1994) The sharpe ratio. J Portfolio Manag 21(1):49–58

    Article  Google Scholar 

  45. Siegler R, Alibali M (2005) Children’s thinking. Prentice Hall, Upper Saddle River

    Google Scholar 

  46. Thawornwong S, Enke D (2004) The adaptive selection of financial and economic variables for use with artificial neural networks. Neurocomputing 56:205–232

    Article  Google Scholar 

  47. Versace M, Bhatt R, Hinds O, Schiffer M (2004) Predicting the exchange traded fund DIA with a combination of genetic algorithms and neural networks. Expert Syst Appl 27(3):417–425

    Article  Google Scholar 

  48. Wang K (2006) Neural network approach to vibration feature selection and multiple fault detection for mechanical systems. Innov Comput Inf Control 3(30):431–434

    Google Scholar 

  49. West D (2000) Neural network credit scoring models. Comput Oper Res 27:1131–1152

    Article  MATH  Google Scholar 

  50. Williams J (1938) The theory of investment value. Harvard University Press, Cambridge

    Google Scholar 

  51. Witten I, Frank E (2005) Data mining. Elsevier, San Francisco

    Google Scholar 

  52. Wong C, Versace M (2011a) Rethinking neural networks in financial decision-making studies: seven cardinal confounds. In: Global conference on business and finance proceedings, Las Vegas, Nevada

  53. Wong C, Versace M (2011) Echo ARTMAP: context sensitivity with neural networks in financial decision-making. Glob J Bus Res 5(5):27–43

    Google Scholar 

  54. Woods D, Knight R (1986) Electrophysiological evidence of increased distractibility after dorsolateral prefrontal lesions. Neurology 36:212–216

    Article  Google Scholar 

  55. Yu L, Wang S, Lai K (2008) Neural network-based mean–variance–skewness model for portfolio selection. Comput Oper Res 35:34–46

    Article  MATH  Google Scholar 

  56. Zhu X, Wang H, Xu L, Li H (2008) Predicting stock index increments by neural networks: the role of trading volume under different horizons. Expert Syst Appl 34:3043–3054

    Article  Google Scholar 

Download references

Acknowledgments

This research was supported by CELEST, an NSF Science of Learning Center (SBE-0354378).

Author information

Authors and Affiliations

  1. Department of Cognitive and Neural Systems, Boston University, 677 Beacon Street, Boston, MA, 02215, USA

    Charles Wong & Massimiliano Versace

Authors
  1. Charles Wong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Massimiliano Versace
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Massimiliano Versace.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wong, C., Versace, M. CARTMAP: a neural network method for automated feature selection in financial time series forecasting. Neural Comput & Applic 21, 969–977 (2012). https://doi.org/10.1007/s00521-012-0830-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-0830-8

Keywords

Search

Navigation