Research on Stock Price Prediction Based on CNN-LSTM Hybrid Neural Network Model

Abstract

In today's era of rapid economic development, the stock market plays an increasingly important role in the overall economic system of the country, and the analysis and prediction of stock prices is one of the most attractive research problems in academia. The analysis and prediction of stock prices is one of the attractive research problems in the current academic world. Neither traditional financial models nor traditional machine learning models can achieve the desired results. In this paper, a CNN-LSTM hybrid neural network model is used to analyze and predict stock prices. The model is trained and validated on three years of Ping An of China stock data, and the experimental data show that the model can achieve relatively excellent prediction accuracy.