Short-term stock market price trend prediction using a comprehensive deep learning system

Area of Science:

• Artificial Intelligence
• Financial Markets
• Data Science

Background:

• Deep learning is increasingly vital for stock market prediction in the big data era.
• Accurate stock trend prediction remains a significant challenge in financial markets.

Purpose of the Study:

• To develop and evaluate a customized deep learning model for predicting Chinese stock market price trends.
• To investigate the impact of comprehensive feature engineering on prediction accuracy.

Main Methods:

• Collected two years of Chinese stock market data.
• Implemented advanced data pre-processing and feature engineering techniques.
• Developed a customized deep learning system for trend prediction.

Main Results:

• The proposed deep learning model with comprehensive feature engineering outperformed standard machine learning models.
• The system achieved high overall accuracy in stock market trend prediction.
• Evaluations confirmed the effectiveness of specific prediction term lengths and pre-processing methods.

Conclusions:

• Customized deep learning models combined with robust feature engineering offer superior stock market trend prediction.
• This research provides valuable insights for both financial and technical domains in stock analysis.
• The findings contribute to advancing predictive modeling in financial big data.