Stock Market Multi-Agent Recommendation System Based on the Elliott Wave Principle
The goal of this paper is to create a hybrid recommendation system based on a Multi-Agent Architecture that will inform the trader about the future stock trend in order to improve the profitability of a short or medium time period investment.
We proposed a Multi-Agent Architecture that uses the numbers of the Fibonacci Series and the Elliott Wave Theory, along with some special Technical Analysis Methods (namely Gap Analysis, Breakout System, Market Modes and Momentum Precedes Price) and Neural Networks (Multi-Layer Perceptron) and tries to combine and / or compare the result given by part / all of them in order to forecast trends in the financial market. In order to validate our model a prototype was developed.
KeywordsMulti-Agent Systems Elliott Wave Theory Technical Analysis Methods Neural Networks Fibonacci Series
- 4.Tirea, M., Tandau, I., Negru, V.: Multi-Agent Stock Trading Algorithm Model. In: SYNASC - 13th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, Timisoara, September 26-29, pp. 365–372 (2011)Google Scholar
- 6.Poser, S.W.: Applying Elliott Wave Theory Profitably. Wiley & Son (2003)Google Scholar
- 7.Ruggiero Jr., M.: Cybernetic Trading Strategies - Developing a Profitable Trading System with State-of-the-Art Technologies. John Wiley & Son (1997)Google Scholar
- 13.Boroden, C.: Fibonacci Trading: How to Master the Time and Price Advantage. McGraw-Hill (2008)Google Scholar