Research on a Linear Regression-Based Model for Stock Movement Analysis

With the rapid growth of the economy, more and more people are speculating in stocks, and usually, stock information can only be viewed on dedicated websites. However, the rapid update of stock data and the limited ability of stockholders to access it through manual access have led to losses in the sector due to information asymmetry in the process of stock speculation. This paper addresses the above problems by studying the implementation of a linear regression-based stock trend analysis model, which classifies stocks into two categories, high quality and poor quality, according to the efficiency of their returns, and uses Python crawler technology and linear regression analysis to improve the accuracy of stock predictions. It allows users to select suitable stocks for purchase based on the aggregation of information, and helps buyers to analyse stock information to a certain extent, select stocks with high yield and avoid investment losses caused by information asymmetry.