Automatic Trading System based on Genetic Algorithm and Technical Analysis for Stock Index

Recent studies in financial markets suggest that technical analysis can be a very useful tool in predicting the trend. Trading systems are widely used for market assessment. This paper employs a genetic algorithm to evolve an optimized stock market trading system. Our proposed system can decide a trading strategy for each day and produce a high profit for each stock. Our decision-making model is used to capture the knowledge in technical indicators for making decisions such as buy, hold and sell. The system consists of two stages: elimination of unacceptable stocks and stock trading construction. The proposed expert system is validated by using the data of 15 stocks that publicly traded in the Thai Stock Exchange 100 Index (SET 100) from the year 2011 through 2014. The experimental results have shown Annual shape Ratio and Return Profits higher than “Buy & Hold” models for each stock index, and the models that used a genetic algorithm to selecting a trading signal has profit better than another models. The results are very encouraging and can be implemented in a Decision-Trading System during the trading day.