Googles Stock Price in Covid-19: An Exploration of Machine Learning Techniques for Prediction

Abstract

The stock market, as well as the global financial and public health systems, were significantly impacted by the abrupt onset of the COVID-19 pandemic. The complicated dynamics caused by the epidemic made it even more difficult to predict stock values. Forecasts from conventional models were less accurate because they have trouble reflecting the psychological characteristics of investors. To increase the accuracy of stock price predictions, researchers investigated machine learning methods like hybrid models and Artificial Neural Networks. In terms of forecasting stock values during crises, there is still a study void. This study study investigates the applicability of decision trees, random forests, and Long Short Term Memory (LSTM) models for analyzing stock market dynamics in the context of an epidemic. Through comparative analysis, it was determined that the LSTM model outperformed the alternative methods, thus establishing its superiority in predictive accuracy. The implications of these findings extend to investors and regulatory bodies, shedding light on the behavior of stock markets during periods of adversity. Subsequent research endeavors should focus on exploring innovative techniques that can further enhance the precision of stock market predictions.