Global, Recurrent and Smoothed-Piecewise Neural Models for Financial Time Series Prediction

S. Yümlü, F.S. Gürgen, and N. Okay (Turkey)


Financial time series prediction (FTSP), Neuralmodels, Mixture of experts (MoE), Istanbul Stock Exchange(ISE), Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH)


This paper makes a comparison of global, feedback and smoothed-piecewise neural prediction models for financial time series prediction (FTSP) 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 ( HR ), positive hit rate ( H+R ), negative hit rate ( H-R ), mean squared error (MSE), mean absolute error (MAE) and correlation (ζ). 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.

Important Links:

Go Back