• The Predictive Power of Price Pattern Recognition in Forex Market ----An automated trading strategy based on pattern extraction and recognation   [MASS 2012]
  • Author(s)
  • Yue Li, Khaldoun M. Khashanah
  • In this paper, we first show that there exist day pattern in the Forex market although Forex is continuously traded. To achieve that, we fold the continuous Forex minute by minute return data into n-by-p matrix and decompose it using PCA. By examining the time series weight distribution (loading factor) of variance from principal component, we confirmed the day patter for EURUSD. Then we try to extract and distinguish different types of return patterns by using cluster method. K-Means and Expectation Maximization with different distance metrics enable us to choose and optimal return pattern. When new observation comes in as stream, the normalized probability of direction change, in the next period, is calculated based on prior likelihood and conditional probability of change of direction given a specific pattern. This mechanism generates a predictive signal. The idea of face recognition by using eigen face is borrowed and integrated in the pattern recognition process. We compare the similarity of feature vector to loading factors and use centroid of clustered patterns as eigen face or base. To examine the power of this pattern recognition in Forex market, we build a trading algorithm and perform back-testing to check its return. Forex data of main currency pairs EURUSD, USDJPY and cross rate currency pair EURJPY are used. As a result, test error, profit & loss and risk adjusted return are compared with K-nearest trajectory method, and sharp ratio from weight adjusted investment strategy outperform KNN.
  • Foreign Exchange, Algorithm trading, Pattern Recognition, Machine Learning, Cluster
  • References
  • [1]
    Irwin, Scott H. and Park, Cheol-Ho. (2007). "What Do We Know About the Profitability of Technical Analysis?" Journal of Economic Surveys, Vol. 21, No. 4, pp. 786-826. Available at SSRN. DOI: 10.1111/j.1467-6419.2007.00519.x.
    Meese and Rogoff, (1983) "Empirical exchange rate models of the seventies. Do they fit out of sample?" Journal of International Economics, Volume 14, Issue 1-2, February 1983, Pages 3-24
    Allen, H., and M.P. Taylor (1990), Charts, Noise and Fundamentals in the Foreign Exchange Market, Economic Journal, 100, pp. 49-59.
    Taylor, M.P. and H. Allen (1992), The Use of Technical Analysis in the Foreign Exchange Market. Journal of International Money and Finance, 11, 304-314.
    Andrew D. Back, Andreas S. Weigend, "A First Application of Independent Component Analysis to Extracting Structure from Stock Returns"
    Utans, J., Holt, W. T. and Refenes, A. N. (1997). Principal component analysis for modeling multi-currency portfolios, in A. S. Weigend, Y. S. Abu-Mostafa and A.-P. N. Refenes (eds), Decision Technologies for Financial Engineering (Proceedings of the Fourth International Conference on Neural Networks in the Capital Markets, NNCM-96), World Scientific, Singapore, pp. 359-368.
    M. I. Jordan and T. Petsche (eds), Advances in Neural Information Processing Systems 9 (NIPS*96), MIT Press, Cambridge, MA, pp. 995-1001.
    Bergerson, Karl, Wunsch Ii, Donald C. (1991) "A commodity trading model based on a neural network-expert system hybrid"
    Saad, E. W., D. V. Prokhorov, et al. (1998). "Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks." IEEE Transactions on Neural Networks 9(6): 1456- 1470.
    Downs T. Hryshko, A. System for foreign exchange trading using genetic algorithms and reinforcement learning. International Journal of Systems Science, 35(13-14):763–774, 2004.
    Germán Creamer,Yoav Freund (2006),"Automated Trading with Boosting and Expert Weighting",Quantitative Finance, Vol. 4, No. 10, pp. 401–420
    Pictet O.V.b Zumbach G.c Bhattacharyya, S.a. Knowledge-intensive genetic discovery in foreign exchange markets. IEEE Transactions on Evolutionary Computation, 6(2):169–181, 2002. cited By (since 1996) 23.
    Florea A. Bucur, L. Techniques for prediction in chaos - a comparative study on financial data. UPB Scientific Bulletin, Series C: Electrical Engineering, 73(3):17–32, 2011.
    Gene Savin, Paul Weller, Janis Zvingelis, The predictive Power of "Head-and-Shoulders" Price Patterns in the U.S Stock Market
    Moody, J. E. and Wu, L. (199713). What is the "true price"? - State space models for high frequency Forex data, Proceedings of the IEEE/IAFE 1997 Conference on Computational Intelligence for Financial Engineering (CIFEr), IEEE Service Center, Piscataway, N J, pp. 150-156.
    Technical Analysis in the Foreign Exchange Market, Christopher J. Neely Paul A. Weller, July 24, 2011

Engineering Information Institute is the member of/source content provider to