Navigating the global stock market: correlation, prediction, and the influence of external factors

Assessing a country’s economic health is a complex task that involves predicting stock price movements. The prices of stocks reflect the overall business climate and the performance of companies. This study examines the relationship between external factors such as weather conditions and pandemic-related data during COVID-19 and global stock prices to enhance comprehension of how worldwide occurrences impact the stock exchange. The analysis reveals that external factors influence stock prices differently, but correlations can provide valuable insights into market dynamics. The research focuses on daily time-series data for various stock indices, including NYSE COMPOSITE, TSX Composite, Nikkei 225, Global X DAX Germany, and HANG SENG INDEX, as well as weather and COVID-19 data. By identifying characteristics that can be correlated with financial market data, the study finds that some factors derived from COVID-19 and weather data have a strong and moderate correlation with daily stock prices. However, it’s important to note that correlation does not necessarily imply causation, even though these insights can be helpful to investors and researchers. For this, the study employs various machine learning and deep learning models to gain a deeper understanding of stock market dynamics in the context of global events. Linear Regression is identified as the top-performing model for NYSE COMPOSITE and TSX Composite in Canada, as well as Germany’s DAX index, with exceptional predictive accuracy. Gradient Boosting Regression proves effective for Japan’s Nikkei 225 index and China’s Hang Seng Index. These findings can be valuable tools for financial analysts and investors who want to enhance their predictive abilities.