Comparison of XGBoost and LSTM Models for Stock Price Prediction

Abstract

Along with the development of technology, machine learning would take up a higher role in analyzing categories. Among those categories, predicting stock price meets the needs of most peopleor most people who trade stocks. By referring to the predicting model, stock traders can decide whether they should trade in or trade out to make a profit in the stock market. Therefore, it is necessary to testify which model can make the prediction with higher accuracy. To analyze this problem, this article examines the performance of different models under different size of datasets. This paper compared XGBoost and LSTM model by collecting stock price data that are 3 years, 6 years, and 9 years ago from the year 2023. Then analyze the close price of stock prices those models. By comparing the figures and calculated rmse value in each year and each model, the impact of different dataset sizes on each model would be revealed. This paper discovered that XGBoost model has greater accuracy under large-size dataset overall, but LSTM can predict more accurate stock price under small-size dataset.