Intelligent Hybrid Stock and Derivative Trading Systems
Using Volatility Modeling, Return Forecasting, and Technical Analysis
Using techniques from the fields of intelligent systems and artificial intelligence, combined with financial theory and historical data, it is possible to develop models that are both predictive and adaptive to changing market conditions. One methodology that has generated success utilizes a generalized regression neural network to develop a hybrid option trading system that incorporates both volatility and return forecasting to predict and trade the S&P 500 stock index. One hybrid sub-system applies a signal from a volatility forecasting system as a primary signal, and then uses various option strategies, such as long and short straddle strategies, to take advantage of the volatility signal. A second sub-system then applies a signal from the return forecasting as a primary signal, using long calls and puts, as well as bull and bear spreading strategies, to take advantage of the forecasting signal. Results show that the hybrid options trading model can improve the overall trading return and can outperform models using return or volatility forecasting in isolation.
Intelligent hybrid stock trading systems that integrate fuzzy logic and genetic algorithm techniques with neural network can also be used to increase the efficiency of stock trading when using a volume adjusted moving average (VAMA), a technical indicator developed from equivolume charting. For the modeling, a neuro-fuzzy based genetic algorithm is used to generate adaptive VAMA membership functions that consider signal ambiguity. Results show that the hybrid intelligent system takes advantage of the synergy among these techniques to generate better stock forecast and trading decisions.
David Enke, Lead Researcher