Multiresolution Forecasting for Futures Trading

In this paper, we investigate the effectiveness of a financial time-series forecasting strategy which exploits the mul- tiresolution property of the wavelet transform. A financial series is decomposed into an over complete, shift invariant scale-related representation. In transform space, each individual wavelet series is modeled by a separate multilayer perceptron (MLP). To better utilize the detailed information in the lower scales of wavelet coef- ficients (high frequencies) and general (trend) information in the higher scales of wavelet coefficients (low frequencies), we applied the Bayesian method of automatic relevance determination (ARD) to choose short past windows (short-term history) for the inputs to the MLPs at lower scales and long past windows (long-term history) at higher scales. To form the overall forecast, the indi- vidual forecasts are then recombined by the linear reconstruction property of the inverse transform with the chosen autocorrelation shell representation, or by another perceptron which learns the weight of each scale in the prediction of the original time series. The forecast results are then passed to a money management system to generate trades. Compared with previous work on combining wavelet techniques and neural networks to financial time-series, our contributions include 1) proposing a three-stage prediction scheme; 2) applying a multiresolution prediction which is strictly based on the autocorrelation shell representation, 3) incorporating the Bayesian technique ARD with MLP training for the selection of relevant inputs; and 4) using a realistic money management system and trading model to evaluate the forecasting performance. Using an accurate trading model, our system shows promising profitability performance. Results comparing the performance of the proposed architecture with an MLP without wavelet preprocessing on 10-year bond futures indicate a doubling in profit per trade ($AUD1753:$AUD819) and Sharpe ratio improvement of 0.732 versus 0.367, as well as significant improvements in the ratio of winning to loosing trades, thus indicating significant potential profitability for live trading. Index Terms—Autocorrelation shell representation, automatic relevance determination, financial time series, futures trading, multilayer perceptron, relevance determination, wavelet decom- position.

[1]  Joseph S. Zirilli.  Financial Prediction Using Neural Networks , 1996 .

[2]  Dominik R. Dersch,et al.  Exchange Rate Trading Using a Fast Retraining Procedure for Generalised Radial Basis Function Networks , 1998 .

[3]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..

[4]  E. Michael Azoff,et al.  Neural Network Time Series: Forecasting of Financial Markets , 1994 .

[5]  Amir B. Geva,et al.  ScaleNet-multiscale neural-network architecture for time series prediction , 1998, IEEE Trans. Neural Networks.

[6]  Robert J. Van Eyden.  The Application of Neural Networks in the Forecasting of Share Prices , 1996 .

[7]  Naoki Saito,et al.  Wavelets, their autocorrelation functions, and multiresolution representations of signals , 1992, Other Conferences.

[8]  W. Sharpe.  The Sharpe Ratio , 1994 .

[9]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[10]  Ashok N. Srivastava,et al.  Nonlinear gated experts for time series: discovering regimes and avoiding overfitting , 1995, Int. J. Neural Syst..

[11]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[12]  Naoki Saito,et al.  Multiresolution representations using the autocorrelation functions of compactly supported wavelets , 1993, IEEE Trans. Signal Process..

[13]  D. Donoho,et al.  Translation-Invariant De-Noising , 1995 .

[14]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  F. Murtagh.  Wedding the Wavelet Transform and Multivariate Data Analysis , 1998 .

[16]  Steven C. Wheelwright,et al.  Forecasting: Methods and Applications, 3rd Ed , 1997 .

[17]  Athanasios Kehagias,et al.  Predictive Modular Neural Networks for Time Series Classification , 1997, Neural Networks.

[18]  Athanasios Kehagias,et al.  Modular neural networks for MAP classification of time series and the partition algorithm , 1996, IEEE Trans. Neural Networks.

[19]  Timothy Masters,et al.  Neural, Novel & Hybrid Algorithms for Time Series Prediction , 1995 .

[20]  Fionn Murtagh,et al.  Wavelet-based feature extraction and decomposition strategies for financial forecasting , 1998 .