Predicting Stock Market Movements in Response to Global Events

Stock market has been using prediction models that have often focused on historical data, giving less attention to how external factors like elections, inflation and conflicts affect the stock prices. This proposal examines the influence possessed by these external factors on stock market behaviour. Machine learning models, including Random Forest, Linear Regression, Gradient Boosting and Long Short-Term Memory (LSTM), is applied as well as investigated on the live dataset of Yahoo Finance, Geopolitical Data, Covid-19 Data and Inflation in GDP, to see which algorithm performs best in predicting the changes in stock value caused by the external factors. The best-case accuracy was 99.9%, showing the importance of consideration of external events for more accurate stock market predictions in the real world. This will help investors make better decisions and improve the risk management strategies required in business.