Forecasting the Dynamics of Stock Market Prices during COVID 19: An Application of ARIMA Modelling U sing Python

The COVID-19 pandemic had a significant effect on worldwide financial markets, resulting in unparalleled instability and unpredictability. This study demonstrates the use of the AutoRegressive Integrated Moving Average (ARIMA) model in Python to predict the fluctuations in stock market values during COVID-19. The main objectives of this study are two-fold: firstly, to examine the influence of COVID-19 on stock market behavior and uncover fundamental patterns, and secondly, to construct a dependable predictive tool to assist investors and stakeholders in making well-informed decisions in these turbulent circumstances. To achieve these objectives, historical stock market data covering the pre-COVID-19 period and the subsequent phases of the pandemic have been preprocessed. After analyzing the data for any discernible trends and seasonality, an appropriate ARIMA model for the time series has been fitted. The python pro-gramming language and its powerful libraries, such as pandas, numpy, and stats models, are employed for data manipulation, visualization, and ARIMA implementation. The findings of the study offer valuable insights into the stock market's response to the pandemic and the efficacy of ARIMA in forecasting prices during such uncertain times. The results indicated that the ARIMA model demonstrates commendable performance in capturing the short-term and medium-term price dynamics. It was found that the pandemic's impact on stock prices extends beyond traditional market indicators, necessitating a data-driven approach to comprehend the market's behavior during this unprecedented period.