Stock Price Prediction During the COVID-19 Pandemic Based on the GRU Algorithm

Abstract

Stock price prediction during the Covid-19 pandemic has emerged as a significant research domain within the financial sector, giving rise to a multitude of neural network-based methods aimed at forecasting stock prices. This paper uses multiple machine learning models and analyzes the stock fund flows to attempt to learn and predict price trends from a dynamic perspective. The data used in this study includes the closing price, change rate, and fund flow of an A-share Pharmaceutical stock in the most recent 1000 trading days. The Mean Squared Error (MSE) is used as the model evaluation metric, and the models MSE can reach 0.013 after training. The predictions generated by the model exhibit a high degree of alignment with the actual price trends, indicating its accuracy in short-term price trend prognostication. These findings substantiate the efficacy of the model for stock price prediction during the pandemic period, thereby contributing to the body of knowledge within the field of financial forecasting.