Skip to main content
Open Access Publications from the University of California


UCLA Electronic Theses and Dissertations bannerUCLA

Stock Trend Prediction: Based on Machine Learning Methods

  • Author(s): Song, Yuan
  • Advisor(s): Wu, Yingnian
  • et al.

Nowadays, people show more and more enthusiasm for applying machine learning methods to finance domain. Many scholars and investors are trying to discover the mystery behind the stock market by applying deep learning. This thesis compares four machine learning methods: long short-term memory (LSTM), gated recurrent units (GRU), support vector machine (SVM), and eXtreme gradient boosting (XGBoost) to test which one performs the best in predicting the stock trend. I chose stock price indicators from 20 well-known public companies and calculated their related technical indicators as inputs, which are the Relative Strength Index, the Average Directional Movement Index, and the Parabolic Stop and Reverse. Experimental results show that recurrent neural network outperforms in time-series related prediction. Especially for gated recurrent units, its accuracy rate is around 5% higher than support vector machine and eXtreme gradient boosting.

Main Content
Current View