A comparison of global, recurrent and smoothed-piecewise neural models for Istanbul stock exchange (ISE) prediction

This paper makes a comparison of global, feedback and smoothed-piecewise neural prediction models for financial time series (FTS) prediction problem. Each model is implemented by various neural network (NN) architectures: global model by a multilayer perceptron (MLP), feedback model by a recurrent neural network (RNN) and smoothed-piecewise model by a mixture of experts (MoE) structure. The advantages and disadvantages of each model are discussed by using real world finance data: 12 years data of Istanbul stock exchange (ISE) index (XU100) from 1990 to 2002. A conventional exponential generalized autoregressive conditional heteroskedasticity (EGARCH) volatility model is also implemented for comparison purpose. The comparison for each model is done based on well-known criterions of index return series of market: hit rate (H"R), positive hit rate (H"R^+), negative hit rate (H"R^-), mean squared error (MSE), mean absolute error (MAE) and correlation (@z). Finally, it is observed that the smoothed-piecewise neural model becomes advantageous in capturing volatility in index return series when it is compared to global and feedback neural model, and also the conventional EGARCH volatility model.

[1]  Jingtao Yao,et al.  Guidelines for Financial Forecasting with Neural Networks , 2001 .

[2]  Lai-Wan Chan,et al.  An Algorithm for Trading and Portfolio Management Using Q-learning and Sharpe Ratio Maximization , 2000 .

[3]  G. Shafer,et al.  Probability and Finance: It's Only a Game! , 2001 .

[4]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[5]  Georg Dorffner,et al.  Risk-neutral density extraction from option prices: improved pricing with mixture density networks , 2001, IEEE Trans. Neural Networks.

[6]  Kenneth Rose,et al.  Mixture of experts regression modeling by deterministic annealing , 1997, IEEE Trans. Signal Process..

[7]  Georg Dorffner,et al.  Temporal pattern recognition in noisy non-stationary time series based on quantization into symbolic streams. Lessons learned from financial volatility trading. , 2000 .

[8]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[9]  Vassilios Petridis,et al.  Predictive Modular Neural Networks: Applications to Time Series , 1998 .

[10]  Fikret S. Gürgen,et al.  Financial Time Series Prediction Using Mixture of Experts , 2003, ISCIS.

[11]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[12]  Athanasios Kehagias,et al.  A Bayesian Multiple Models Combination Method for Time Series Prediction , 2001, J. Intell. Robotic Syst..

[13]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[14]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[15]  Oscar Castillo,et al.  Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic, and fractal theory , 2002, IEEE Trans. Neural Networks.

[16]  F. Delbaen.  Probability and Finance: It's Only a Game! , 2002 .