paper available: financial prediction

[Lee Giles]

The following technical report and related conference paper 
is now available at the WWW sites listed below:

www.neci.nj.nec.com/homepages/lawrence/papers.html
www.neci.nj.nec.com/homepages/giles/#recent-TRs
www.cs.umd.edu/TRs/TRumiacs.html

We apologize in advance for any multiple postings that may occur.

**************************************************************************

     Noisy Time Series Prediction using Symbolic Representation and
            Recurrent Neural Network Grammatical Inference

     U. of Maryland Technical Report CS-TR-3625 and UMIACS-TR-96-27

       Steve Lawrence (1), Ah Chung Tsoi (2), C. Lee Giles (1,3)

(1) NEC Research Institute, 4 Independence Way, Princeton, NJ 08540, USA
(2) Faculty of Informatics, University of Wollongong, NSW 2522 Australia
(3) Institute for Advanced Computer Studies, University of Maryland,
    College Park, MD 20742, USA

                              ABSTRACT

Financial forecasting is an example of a signal processing problem
which is challenging due to small sample sizes, high noise,
non-stationarity, and non-linearity.  Neural networks have been very
successful in a number of signal processing applications.  We discuss
fundamental limitations and inherent difficulties when using neural
networks for the processing of high noise, small sample size signals.
We introduce a new intelligent signal processing method which
addresses the difficulties. The method uses conversion into a symbolic
representation with a self-organizing map, and grammatical inference
with recurrent neural networks. We apply the method to the prediction
of daily foreign exchange rates, addressing difficulties with
non-stationarity, overfitting, and unequal a priori class
probabilities, and we find significant predictability in comprehensive
experiments covering 5 different foreign exchange rates. The method
correctly predicts the direction of change for the next day with an
error rate of 47.1%.  The error rate reduces to around 40% when
rejecting examples where the system has low confidence in its
prediction. The symbolic representation aids the extraction of
symbolic knowledge from the recurrent neural networks in the form of
deterministic finite state automata. These automata explain the
operation of the system and are often relatively simple. Rules related
to well known behavior such as trend following and mean reversal are
extracted.

Keywords - noisy time series prediction, recurrent neural networks,
self-organizing map, efficient market hypothesis, foreign exchange
rate, non-stationarity, efficient market hypothesis, rule extraction


**********************************************************************

A short published conference version:
 
C.L. Giles, S. Lawrence, A-C. Tsoi, "Rule Inference for Financial
Prediction using Recurrent Neural Networks," Proceedings of the
IEEE/IAFE Conf. on Computational Intelligence for Financial
Engineering, p. 253, IEEE Press, 1997.

can be found at

www.neci.nj.nec.com/homepages/lawrence/papers.html
www.neci.nj.nec.com/homepages/giles/papers/IEEE.CIFEr.ps.Z

__                                
C. Lee Giles / Computer Science / NEC Research Institute / 
4 Independence Way / Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482
www.neci.nj.nec.com/homepages/giles.html
==