Performance evaluation of neural network architectures: the case of predicting foreign exchange correlations

Abstract

In the last decade, neural networks have emerged from an esoteric instrument in academic research to a rather common tool assisting auditors, investors, portfolio managers and investment advisors in making critical financial decisions. It is apparent that a better understanding of the network's performance and limitations would help both researchers and practitioners in analysing real-world problems. Unlike many existing studies which focus on a single type of network architecture, this study evaluates and compares the performance of models based on two competing neural network architectures, the multi-layered feedforward neural network (MLFN) and general regression neural network (GRNN). Our empirical evaluation measures the network models' strength on the prediction of currency exchange correlation with respect to a variety of statistical tests including RMSE, MAE, U statistic, Theil's decomposition test, Henriksson-Merton market timing test and Fair-Shiller informational content test. Results of experiments suggest that the selection of proper architectural design may contribute directly to the success in neural network forecasting. In addition, market timing tests indicate that both MLFN and GRNN models have economically significant values in predicting the exchange rate correlation. On the other hand, informational content tests discover that the neural network models based on different architectures capture useful information not found in each other and the information sets captured by the two network designs are independent of one another. An auxiliary experiment is developed and confirms the possible synergetic effect from combining forecasts made by the two different network architectures and from incorporating information from an implied correlation model into the neural network forecasts. Implied correlation and random walk models are also included in our empirical experiment for benchmark comparison. Copyright © 2005 John Wiley & Sons, Ltd.

Prediction of Financial Crisis with Artificial Neural Network: An Empirical Analysis on Turkey

“…MLFN with supervised learning can be used to develop nonlinear models to indicate the relationship between the independent and the dependent variables. (Chen and Leung, 2005) In this paper, the data of 298 months between January 1990 and September 2014, obtained from the internet sites of Electronic Data Distribution System of the Turkish National Bank (EDDS) and The World Bank, were used. In the empirical analysis part, seven different variables, which are US Dollar (USD), gold prices (GP), Borsa Istanbul (BIST) 100 Index, wholesale price index (WPI), money supply (MS), domestic debt stock (DDS), composite leading economic indicators index (CLEI) were used.…”

Gold price forecasting with a neuro-fuzzy-based inference system

“…The use of neural networks is not new in forecasting the price of gold, stock market indexes and individual assets (McCann and Kalman, 1994;Tsibouris and Zeidenberg, 1995;Chen and Leung, 2005). Many researchers have used non-linear techniques, have compared them with traditional linear regression analysis and concluded in favour of precious metals being non-linear in nature.…”

Predicting financial time series data using artificial immune system-inspired neural networks

“…Financial service companies are becoming more and more dependent on computer technologies to establish and maintain competitiveness in the rapidly expanding global economy (Chen and Leung, 2005). Illustrating the point, researchers have identified that several large investment banks (including Goldman Sachs and Morgan Stanley) now have departments dealing solely with the neural network models required for their business investment analysis (Shachmurove and Witkowska, 2000).…”

“…Accordingly, throughout the last decade, neural networks have gained ground, moving from research experimentation tools, through to production and industrial decision-support systems; assisting managerial and advisory staff in making 'critical financial decisions' (Chen and Leung, 2005). As such, they are regarded as powerful tools for forecasting data, and have significant academic/research interest from fields such as artificial intelligence, machine learning, and statistics.…”