Comparative Study of Artificial Neural Networks and Hidden Markov Model for Financial Time Series Prediction
Article Sidebar
Main Article Content
Abstract
Financial Time Series analysis and prediction is
one of the interesting areas in which past data could be used
to anticipate and predict data an d information about future.
There are many artificial intelligence approaches used in the
prediction of time series, such as Artificial Neural Networks
(ANN) and Hidden Markov Models (HMM). In this paper
HMM and HMM approaches for predicting financial time
series are presented. ANN and HMM are used to predict
time series that consists of highest and lowest Forex index
series as input variable. Both of ANN and HMM are trained
on the past dataset of the chosen currencies (such as EURO/
USD which is used in this paper). The trained ANN and
HMM are used to search for the variable of interest
behavioral data pattern from the past dataset. The obtained
results was compared with real values from Forex (Foreign
Exchange) market database [1]. The power and predictive
ability of the two models are evaluated on the basis of Mean
Square Error (MSE). The Experimental results obtained are
encouraging, and it demonstrate that ANN and HMM can
closely predict the currency market, with a small different
in predicting performance
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
"FXCM Trading St at ion Program," 01.08.040910 ed: FXCM,
"Bank of Int ernat ional Sett lement ," Triennial Cent ral Bank
Survey - Foreign exchange and derivat ives market act ivit y in
R. J. Kuo, L. C. Lee, and C. F. Lee, "Int egrat ion of Art ificial
Neural Net works and Fuzzy Delphi for Stock Market
Forecast ing," in IEEE International Conference on Systems,
Man, and Cybernetics, 1996, pp. 1073-1078.
E. H. K. Fung and A. P. L. Chung, "Using ARMA Models to
Forecast Workpiece Roundness Error in a Turning Operation,"
Applied Mathematical Modelling, Vol. 23, pp. 567-585, 1999. DOI: https://doi.org/10.1016/S0307-904X(98)10100-2
M. H. Eng, Y. Li, Q. G. Wang, and T. H. Lee, "Forecast Forex
wit h Artificial Neural Net work Using Fundamental Dat a," 2009,
pp. 279-282.
A. K. Lohani, N. K. Goel, and K. K. S. Bhat ia, "Development of
Fuzzy Logic Based Real Time Flood Forecast ing Syst em for
River Narmada in Central India," 2005.
E. Abbasi and A. Abouec, "Stock Price Forecast by Using
Neuro-Fuzzy Inference Syst em," 2008, pp. 320-323.
K. Kim, "Financial Time Series Forecast ing Using Support
Vect or Machines," Neurocomputing, vol. 55, pp. 307-319, 2003. DOI: https://doi.org/10.1016/S0925-2312(03)00372-2
K. Slany, "Towards the Automat ic Evolut ionary Predict ion of the
FOREX Market Behaviour," 2009, pp. 141-145.
M. R. Hassan and B. Nath, "Stock Market Forecast ing using
Hidden Markov Model: A New Approach," in Proceedings 5th
International Conference on Intelligent Systems Design and
Applications (ISDA'05), 2005, pp. 192-196.
S. Haykin. Neural Net works, A Comprehensive Foundat ion,
New York, Macmillan Publishing., 1994.
R. Nag, K. Wong, and F. Fallside, "Script Recognit ion using
Hidden Markov Models," in IEEE International Conference on
Acoustics, Speech, and Signal Processing (ICASSP'86), 1986,
pp. 2071-2074.
Y. Bengio, Y. LeCun, C. Nohl, and C. Burges, "A NN/HMM
Hybrid for On-Line Handwrit ing Recognit ion," Neural
Computation, vol. 7, pp. 1289-1303, 1995. DOI: https://doi.org/10.1162/neco.1995.7.6.1289
A. Krogh, M. Brown, I. S. Mian, K. Sj olander, and D. Haussler,
"Hidden Markov models in Comput ational Biology: Applicat ions
to Prot ein Modelling," J. Mol. Biol, Vol. 235, pp. 1501-1531,
P. Baldi and S. Brunak, Bioinformatics: The Machine Learning
Approach: The MIT Press, 2001.
P. Smyth, "Hidden Markov Models for Fault Det ect ion in
Dynamic Syst ems," Pattern Recognition, vol. 27, pp. 149-164,
A. Shaaib, Foreign Exchange Forecast ing using Hidden Markov
Model, Mast er Thesis, The Libyan Academy, 2014.
K. Y. Lee, Y. T. Cha and J. H. P ark, “ Short -Term Load
Forecast ing using an Art ificial Neural Net work,” Transact ions on
power syst ems, Vol. 7, No. 1, February 1992.
D. E. Rumelhart , G. E. Hinton and R. J. Williams, “Learning
Int ernal represent at ion by error propagat ion,” P arallel Distribut ed
Processing, vol. 1, pp. 318-362, Cambridge, MA: MIT Press,
L. R. Rabiner, "A Tutorial on Hidden Markov Models and
Select ed Applicat ions in Speech Recognit ion," Proceedings of
the IEEE, vol. 77, pp. 257-286, 1989. DOI: https://doi.org/10.1109/5.18626