Applied Random Forest Algorithm for News and Article Features on The Stock Price Movement: An Empirical Study of The Banking Sector in Vietnam

Abstract

In 2023, in the context of the world economic and political situation continuing to experience many difficulties and challenges, the global stock market has suffered many unfavorable impacts. In that general context, Vietnam's stock market faces many problems, challenges, and strong fluctuations due to unexpected changes in the world's macro economy and geopolitics. Therefore, the study's goal is to investigate the impact of news articles on the stock price movement of commercial banks in Vietnam. Using a dataset of 94,784 news articles from January 2023 to April 2024 and applying the Random Forest algorithm, the author analyzes the significance of various news features. The study identifies that the proportion of news sources with positive evaluations and the proportion of news sources mentioning commercial banks are the most influential features of the stock price movement. The findings reveal that positive news boosts investor confidence, increasing stock prices, while high media attention significantly influences trading activity. Other notable features include the number of news sources and the total sentiment score of articles, which also play crucial roles. This research provides valuable insights for investors and analysts to understand the effect of news articles on stock prices, enhancing their decision-making process in the banking sector. Finally, the research results are scientific proof that helps the Vietnamese stock market to have more positive and robust changes, continue to be an attractive destination for domestic and foreign investment capital flows, and a channel for medium and long-term capital important term for the economy, making an increasingly more outstanding contribution to the country's socio-economic development in the new era.