Research on stock trading prediction based on MAD and Q-learning

Abstract

The accuracy of traditional stock trading prediction is lacking, and stock trading is risky, so this study tries to use machine learning models for stock trading change prediction in big data. This study proposes an algorithm based on the combination of the MAD (Median Absolute Deviation) method and Q-learning model to improve the accuracy of predicting stock trades. The simulation results based on "^GSPC" data show that the new method can better help predict stocks. Of course, this study has some limitations, as the method currently adopts a combination of traditional econometric models and machine learning models, which has some efficiency problems. However, the method proposed in this study is innovative and can provide new ideas for stock price trend prediction and provide new research methods and perspectives for stock market practitioners.