Deep Feature Extraction for Financial Time Series Prediction via Convolutional Neural Networks

Abstract

This study proposes a stock market trend prediction model based on convolutional neural network (CNN), which is trained using historical stock price data to predict future stock market trends. By comparing models such as support vector machine (SVM), long short-term memory network (LSTM), random forest (RF) and multi-layer perceptron (MLP), the experimental results show that CNN outperforms other models in evaluation indicators such as mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE), showing strong prediction accuracy and stability. This method can effectively extract complex trend patterns from stock market data and provide a more accurate and reliable solution for stock market prediction.