Chinese stock price prediction under COVID-19 period based on linear Regression Model

Abstract

To anticipate and assess the price trend of scientific and technical stocks in a time of high volatility following the breakdown of China's COVID-19 Epidemic Economic Policy at the end of 2022, we plan to utilize a training linear regression model in this work. assisting people and businesses in making better analyses and decisions during this time of high risk, thereby lowering investment risks. This paper uses the stock price data of Alibaba, Tencent, and Xiaomi in Quandl during the new crown epidemic to represent the general trend of Chinese technology stock prices. We preprocessed the data to retain features that better reflect the characteristics of the data and remove features that have less impact on the data analysis. This study chose a linear regression model to model various relationships through the classifier used by Scikit-Learn for regression and estimated the unknown parameters in the linear regression model from the data. The data from the training and test sets are used to train the linear regression model, and the results are visualized as graphs, which can more intuitively convey the overall trend and local volatility of stock prices. In this study, the accuracy of the model can reach more than 85%. The visualized figure shows that although stock values recovered quickly when the regulation was lifted, they are still lower than they were before the outbreak due to the impact of China's past epidemic policies on their long-term fall. The experimental findings demonstrate the great accuracy with which the advanced regression model in this work can forecast the price trend of technology stocks throughout the period of high volatility following the policy's unsealing and the extent to which it may represent price volatility.