Applying Independent Component Analysis and Predictive Systems for Algorithmic Trading
- 326 Downloads
In this paper, a Nonlinear AutoRegressive network with eXogenous inputs and a support vector machine are proposed for algorithmic trading by predicting the future value of financial time series. These architectures are capable of modeling and predicting vector autoregressive VAR(p) time series. In order to avoid overfitting, the input is pre-processed by independent component analysis to filter out the most noise like component. In this way, the accuracy of the prediction and the trading performance is increased. The proposed algorithms have a small number of free parameters which makes fast learning and trading possible. The method is not only tested on single asset price series, but also on predicting the value of mean reverting portfolios obtained by maximizing the predictability parameter of VAR(1) processes. The tests were first performed on artificially generated data and then on real data selected from exchange traded fund time series including bid–ask spread. In both cases the proposed method could achieve positive returns.
KeywordsAlgorithmic trading Financial time series Neural network Support vector machine Independent component analysis Mean reverting portfolio
- Aalto University, D.o.C.S. (2015). The fastica package for matlab. http://research.ics.aalto.fi/ica/fastica/.
- Alpaydin, E. (2010). Introduction to machine learning (2nd ed.). Cambridge: The MIT Press.Google Scholar
- Back, A. D., & Weigend, A. S. (1998). Decision technologies for computational finance. In Proceedings of the fifth international conference computational finance, chapter discovering structure in finance using independent component analysis (pp. 309–322). Boston, MA: Springer.Google Scholar
- Chan, E. (2013). Algorithmic trading: Winning strategies and their rationale (1st ed.). Hoboken, NJ: Wiley Publishing.Google Scholar
- Chang, C. C. & Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2, 27:1–27:27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
- d’Aspremont, A. (2007). Identifying small mean reverting portfolios. CoRR abs/0708.3048.Google Scholar
- Johnson, R. A., & Wichern, D. W. (Eds.). (1988). Applied multivariate statistical analysis. Upper Saddle River, NJ: Prentice-Hall Inc.Google Scholar
- Kumar, P. N., Seshadri, G. R., Hariharan, A., Mohandas, V. P. & Balasubramanian, P. (2011). Technology systems and management. In First international conference, ICTSM 2011, Mumbai, India, February 25–27, 2011. Selected papers, chapter financial market prediction using feed forward neural network, (pp. 77–84). Berlin, Heidelberg: Springer.Google Scholar
- Lahmiri, S. (2011). A comparison of pnn and svm for stock market trend prediction using economic and technical information. International Journal of Computer Applications, 29(3), 24–30.Google Scholar
- Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77–91.Google Scholar
- Wilamowski, B. M., & Irwin, J. D. (2011). Intelligent systems (2nd ed.). Boca Raton, FL: CRC Press Inc.Google Scholar
- Yahoo (2015). Yahoo! finance. https://finance.yahoo.com.