A Two-level Cascade Evolutionary Computation based Covered Call Trading Model

In this study, a two-level cascade stock trading model is proposed. In the first level, the buy/sell signals are created by optimizing the RSI technical indicator parameters with evolutionary computation techniques. Then using the selected parameters, in the second level actual trading is performed using an optimized covered call strategy. Again, the optimization is implemented with evolutionary computation. In this particular study, genetic algorithms (GA) and Particle Swarm Optimization (PSO) are chosen as the soft computing methods for optimization. Historical end-of-day close values and options data for the S&P 500 Spider ETF (SPY) and 4 other ETFs (EWZ, XLE, IWM, XLF) between years 2005-2009 are used. The system is trained using the data between 2005 and 2008; the testing is done with 2009 data. The results indicate that the proposed model outperformed not only the buy and hold strategy, but also buying and selling the ETF alone without the options. In future work different stock/ETF data and different combined options strategies will be included in the model to identify performances of different techniques.