A CNN-Based Method for AAPL Stock Price Trend Prediction Using Historical Data and Technical Indicators

The stock price is a non-stationary time series, so it is challenging to predict the stock price. Some statistics and machine learning research hope to solve this problem, but these methods require complex feature engineering. Deep learning without feature extraction has brought a breakthrough for this. This paper uses the convolutional neural network (CNN) to establish a three-category prediction model based on historical stock prices and technical analysis indicators to predict stock price trends. Experiments conducted on AAPL show that adding technical indicators can improve the performance of the CNN prediction model.