A new SAX-GA methodology applied to investment strategies optimization

This paper presents a new computational finance approach, combining a Symbolic Aggregate approXimation (SAX) technique together with an optimization kernel based on genetic algorithms (GA). The SAX representation is used to describe the financial time series, so that, relevant patterns can be efficiently identified. The evolutionary optimization kernel is here used to identify the most relevant patterns and generate investment rules. The proposed approach was tested using real data from S&P500. The achieved results show that the proposed approach outperforms both B&H and other state-of-the-art solutions.

[1]  Nuno Horta,et al.  Trading with optimized uptrend and downtrend pattern templates using a genetic algorithm kernel , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[2]  Nuno Horta,et al.  Fitness function evaluation for MA trading strategies based on genetic algorithms , 2011, GECCO '11.

[3]  Hanif Tahersima,et al.  Forecasting Stock Exchange Movements Using Neural Networks: A Case Study , 2011, 2011 International Conference on Future Computer Sciences and Application.

[4]  Christos Faloutsos,et al.  Efficient Similarity Search In Sequence Databases , 1993, FODO.

[5]  Tak-Chung Fu,et al.  Stock time series visualization based on data point importance , 2008, Eng. Appl. Artif. Intell..

[6]  Shingo Mabu,et al.  Enhancing global portfolio optimization using genetic network programming , 2010, Proceedings of SICE Annual Conference 2010.

[7]  Qiang Wang,et al.  Stock Market Prediction Using Artificial Neural Networks Based on HLP , 2011, 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics.

[8]  Eamonn J. Keogh,et al.  Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases , 2001, Knowledge and Information Systems.

[9]  Jessica Lin,et al.  Finding Motifs in Time Series , 2002, KDD 2002.

[10]  Peter L. Bernstein.  A New Look at the Efficient Market Hypothesis , 1999 .

[11]  Dina Q. Goldin,et al.  On Similarity Queries for Time-Series Data: Constraint Specification and Implementation , 1995, CP.

[12]  Patrick P. K. Chan,et al.  Stock investment decision support for Hong Kong market using RBFNN based candlestick models , 2011, 2011 International Conference on Machine Learning and Cybernetics.

[13]  Hua-Ning Hao.  Notice of RetractionShort-term forecasting of stock price based on genetic-neural network , 2010, 2010 Sixth International Conference on Natural Computation.

[14]  Zhijun Fang,et al.  Stock Forecast Method Based on Wavelet Modulus Maxima and Kalman Filter , 2010, 2010 International Conference on Management of e-Commerce and e-Government.

[15]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[16]  Kazuhiro Matsui,et al.  Neighborhood evaluation in acquiring stock trading strategy using genetic algorithms , 2010, 2010 International Conference of Soft Computing and Pattern Recognition.

[17]  Andreas Krause.  Performance of evolving trading strategies with different discount factors , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).