Buy-sell strategy model construction with Hybrid XCS

Many financial time series forecasting techniques have been so far developed for predicting stock prices. However, only with the forecasting value of the next time, it is difficult to determine the optimal buy-sell strategy and get benefit. On the other hand, because the financial time series change severely, it can hardly be identified by a single global model. One model will just be suitable for some kinds of changing patterns, but fail on other patterns. Then, in this paper, we proposed a Hybrid XCS (eXtended Classifier System) learning method by adopting multiple local models. Each local model is called Slaver-Agent and trained with XCS method. A unique Master-Agent chooses which Slaver-Agent is the most effectively for a given changing pattern. With the hybrid learning structure, multiple Slaver-Agents work alternately, and the limitation of learning by one single agent can be overcome. Their learning objective is to obtain profitable transaction decisions directly and get maximum return benefit after several transactions. Experiments have been performed on several well known securities, and the results have been compared with a single agent and some traditional Technical Analysis strategies.

[1]  Osamu Katai,et al.  Analyzing Real-valued Learning Classifier Systems: Validating Real-valued Representations and its Parameter Sensitivity for XCS , 2005 .

[2]  Martin V. Butz,et al.  An Algorithmic Description of XCS , 2000, IWLCS.

[3]  John H. Holland,et al.  Cognitive systems based on adaptive algorithms , 1977, SGAR.

[4]  Stewart W. Wilson,et al.  Learning Classifier Systems, From Foundations to Applications , 2000 .

[5]  Fabio Roli,et al.  Stock Market Prediction by a Mixture of Genetic-Neural Experts , 2002, Int. J. Pattern Recognit. Artif. Intell..

[6]  Filippo Castiglione.  Forecasting Price increments using an Artificial Neural Network , 2001, Adv. Complex Syst..

[7]  D.E. Goldberg,et al.  Classifier Systems and Genetic Algorithms , 1989, Artif. Intell..

[8]  Peter Ross,et al.  An Adaptive Agent Based Economic Model , 1999, Learning Classifier Systems.

[9]  Tomoharu Nagao,et al.  Adaptive XCSM for Perceptual Aliasing Problems , 2005, ICNC.

[10]  Ganesh Mani,et al.  Financial Forecasting Using Genetic Algorithms , 1996, Appl. Artif. Intell..

[11]  Franklin Allen,et al.  Using genetic algorithms to find technical trading rules , 1999 .

[12]  P. Lanzi.  Extending the representation of classifier conditions part I: from binary to messy coding , 1999 .

[13]  Chung-Ming Kuan,et al.  Forecasting exchange rates using feedforward and recurrent neural networks , 1992 .

[14]  Xavier Llorà,et al.  Data Mining using Learning Classifier Systems , 2004 .

[15]  平澤 宏太郎,et al.  Genetic Network Programming によるヘテロマルチエージェントシステムの構成 , 2003 .

[16]  Peter Ross,et al.  Strength and Money: An LCS Approach to Increasing Returns , 2000, IWLCS.

[17]  Stewart W. Wilson.  Classifier Fitness Based on Accuracy , 1995, Evolutionary Computation.

[18]  Peter Ross,et al.  Explorations in LCS Models of Stock Trading , 2001, IWLCS.

[19]  Luca Lanzi Pier,et al.  Extending the Representation of Classifier Conditions Part II: From Messy Coding to S-Expressions , 1999 .