| dc.description.abstract | The purpose of this paper is to explore how to use techniques such as up and down statistical method, suffix tree data structure, and genetic algorithm to achieve stock price analysis, in order to improve the accuracy and stability of stock price prediction. The main sources of data were IEEE papers and stock selection related books on the market. The research method used suffix tree data structure and genetic algorithm to obtain more accurate and stable prediction results. In backtesting historical data, the highest accuracy rate can reach over 61%. After experiments, it was found that different algorithms are suitable for different types of stocks. The up and down statistical method is suitable for growth stocks, suffix tree is suitable for cyclical stocks, and genetic algorithm is suitable for any type of stocks, although the winning rate is not the highest, the prediction results are more stable. Therefore, choosing the appropriate algorithm is very important in practical applications, which can improve the accuracy and reliability of stock price prediction. In summary, this paper discusses the methods of implementing stock price analysis using different algorithms, and has achieved some results through backtesting historical data. Future research can further explore the applicable scope, accuracy, and stability of different algorithms to improve the accuracy and reliability of stock price prediction. | en_US |