Multi-agent FX-Market Modeling Based on Cognitive Systems

We present an approach ofm ulti-agent market modeling on the basis of cognitive systems with three functionality features. These features are perception, internal processing and acting. A cognitive system is structurally represented by an error correction neural network. On the mirco-level we describe agents decisions behavior by combining cognitive systems with a framework of multi-agent market modeling. By aggregating agents decisions we are able to capture the underlying market dynamics on the macro-level. As an application, we apply our approach to the DEM / USD FX-Market. Fitting real-world data, our approach is superior to more conventional forecasting techniques.

[1]  Rudolf Kruse,et al.  Neuro Fuzzy Systems for Data Analysis , 1999 .

[2]  Ralph Neuneier,et al.  Modeling Dynamical Systems by Error Correction Neural Networks , 2002 .

[3]  Ralph Neuneier,et al.  Active Portfolio-Management based on Error Correction Neural Networks , 2001, NIPS.

[4]  Georg Zimmermann,et al.  Market Modeling Based on Cognitive Agents , 2002, ICANN.

[5]  Joshua M. Epstein,et al.  Growing artificial societies , 1996 .

[6]  Ralph Neuneier,et al.  Combining State Space Reconstruction and Forecasting by Neural Networks , 2000 .

[7]  S. Grossberg.  Neural Networks and Natural Intelligence , 1988 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Euan M. Macphail,et al.  The evolution of consciousness , 1998 .

[10]  Ralph Neuneier,et al.  Undershooting: modeling dynamical systems by time grid refinements , 2002, ESANN.

[11]  Ralph Grothmann,et al.  Multi agent market modeling based on neutral networks , 2002 .

[12]  Thomas Metzinger,et al.  Conference on Neural Correlates of Consciousness: Empirical and Conceptual Questions , 1998, Consciousness and Cognition.

[13]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[14]  M. Embrechts,et al.  Exchange Rate Theory: Chaotic Models of Foreign Exchange Markets , 1993 .

[15]  Hans-Georg Zimmermann,et al.  Yield curve forecasting by error correction neural networks and partial learning , 2002, ESANN.

[16]  Blake LeBaron,et al.  Agent-based computational finance : Suggested readings and early research , 2000 .

[17]  Fu-Sheng Tsung,et al.  Modeling dynamical systems with recurrent neural networks , 1994 .

[18]  Ralph Neuneier,et al.  Modeling of the German Yield Curve by Error Correction Neural Networks , 2000, IDEAL.

[19]  Ralph Neuneier,et al.  Multi-agent modeling of multiple FX-markets by neural networks , 2001, IEEE Trans. Neural Networks.

[20]  Barak A. Pearlmutter.  Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[21]  Ralph Neuneier,et al.  The Observer-Observation Dilemma in Neuro-Forecasting , 1997, NIPS.