Prediction based – High Frequency Trading on Financial Time Series

Farhad Kia, Janos Levendovszky

2013

Abstract

In this paper we investigate prediction based trading on financial time series assuming general AR(J) models and mean reverting portfolios. A suitable nonlinear estimator is used for predicting the future values of a financial time series will be provided by a properly trained FeedForward Neural Network (FFNN) which can capture the characteristics of the conditional expected value. In this way, one can implement a simple trading strategy based on the predicted future value of an asset price or a portfolio and comparing it to the current value. The method is tested on FOREX data series and achieved a considerable profit on the mid price. In the presence of the bid-ask spread, the gain is smaller but it still ranges in the interval 2-6 percent in 6 months without using any leverage. FFNNs were also used to predict future values of mean reverting portfolios after identifying them as Ornstein-Uhlenbeck processes. In this way, one can provide fast predictions which can give rise to high frequency trading on intraday data series.

References

  1. A Hanif, R., 2012. Algorithmic, Electronic and Automated Trading.
  2. Box, G. E., Tiao, G.C. , 1977. A canonical analysis of multiple time series.
  3. D'Aspremont, A., 2011. Identifying small mean-reverting portfolios.
  4. J. W., 2002. Portfolio and Consumption Decisions under Mean-Reverting Returns: An Exact Solution for Complete Markets.
  5. Kissell, R., 2006. Algorithmic trading strategies.
  6. L., C., 2012. Predictability and Hedge Fund Investing..
  7. Peter Bergan, C., 2005. Algorithmic Trading What Should You Be Doing?.
  8. Pole, A., 2007. Algorithmic trading insights and techniques.
  9. R. Balvers, Y. W., E Gilliland , 2000. Mean Reversion across National Stock Markets and Parametric Contrarian Investment Strategies.
  10. R. L. Naik, D. R., B Manjula, A Govardhan, 2012. Prediction of Stock Market Index Using Genetic Algorithm.
  11. Y. Zuo, E. K., 2012. Up/Down Analysis of Stock Index by Using Bayesian Network.
Download


Paper Citation


in Harvard Style

Kia F. and Levendovszky J. (2013). Prediction based – High Frequency Trading on Financial Time Series . In Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013) ISBN 978-989-8565-77-8, pages 502-506. DOI: 10.5220/0004555005020506


in Bibtex Style

@conference{ncta13,
author={Farhad Kia and Janos Levendovszky},
title={Prediction based – High Frequency Trading on Financial Time Series},
booktitle={Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)},
year={2013},
pages={502-506},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004555005020506},
isbn={978-989-8565-77-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2013)
TI - Prediction based – High Frequency Trading on Financial Time Series
SN - 978-989-8565-77-8
AU - Kia F.
AU - Levendovszky J.
PY - 2013
SP - 502
EP - 506
DO - 10.5220/0004555005020506