A COMPARATIVE STUDY ON EFFECT OF COVID-19 ON SELECTED GLOBAL STOCK

The COVID-19 pandemic, which emerged in late 2019 and rapidly escalated into a global crisis by early 2020, triggered unprecedented disruptions across economies, industries, and financial systems. Among the most immediate and visible impacts was the volatility observed in global stock markets. This research undertakes a comprehensive and comparative study of how COVID-19 affected selected global stock exchanges—including but not limited to the New York Stock Exchange (NYSE), London Stock Exchange (LSE), Tokyo Stock Exchange (TSE), National Stock Exchange of India (NSE), and Shanghai Stock Exchange (SSE)—during the initial outbreak and throughout key phases of the pandemic. The aim of the study is to assess both short-term shocks and long-term market behavior, analyzing how different economies and investor sentiment responded to pandemic-induced lockdowns, fiscal stimulus measures, supply chain disruptions, and changes in consumer behavior. By applying both traditional financial tools (such as return analysis, volatility indices, and beta coefficients) and advanced software-driven techniques—including machine learning models for trend prediction, sentiment analysis using NLP, and deep learning models for time series forecasting—this research provides a robust analysis of stock market reactions under extreme uncertainty. The study examines daily closing prices, trading volumes, and market indices before, during, and after major COVID-19 milestones (such as WHO’s pandemic declaration, vaccine rollouts, and economic recovery phases). Statistical techniques such as event study methodology, GARCH (Generalized Autoregressive Conditional Heteroskedasticity) modeling, and VAR (Vector Autoregression) are used to quantify volatility and inter-market correlations. Furthermore, sentiment scores derived from financial news headlines, press releases, and social media platforms are integrated using Natural Language Processing (NLP) to understand the psychological drivers of stock market behavior. Results reveal that markets with strong digital infrastructures and robust policy responses (such as the U.S. and China) experienced faster recoveries, while others with structural economic vulnerabilities showed slower rebounds. Sector-wise, technology, healthcare, and ecommerce stocks outperformed during lockdowns, whereas aviation, tourism, and energy sectors were heavily impacted. The analysis also highlights how investor behavior shifted from traditional assets to digital alternatives, including crypto currencies, during periods of extreme volatility. This research concludes that while COVID-19 was a black swan event, it accelerated the digital transformation of financial markets and underscored the importance of agility, data-driven forecasting, and behavioral finance. The study also identifies how AI-driven tools and machine learning algorithms can aid in crisis forecasting, portfolio optimization, and risk mitigation. As the world transitions into a post-pandemic economic environment, the findings of this study serve as a critical reference for policymakers, institutional investors, and global corporations in designing resilient financial strategies.