Data-Driven Analysis and Forecasting of COVID-19 Third Wave in SAARC Countries

COVID-19 is a global pandemic that has affected millions of people worldwide. Effective forecasting of the spread of COVID-19 is crucial for proactive planning, public health interventions, adopting vaccination strategies, and raising public awareness. It enables a more effective and coordinated response to the pandemic, ultimately saving lives and reducing the impact on societies. Like many other parts of the globe, the eight coun-tries under the ‘South Asian Association for Regional Cooperation’ (SAARC) have faced different challenges in dealing with the repeated waves of this pandemic. In this paper, we have analyzed the aftermath of COVID-19's third wave in SAARC countries and proposed a model for forecasting future situations using Machine Learning (ML) algorithms. We have used data from various sources to visualize and compare the cases, tests, deaths, and vaccinations in each of the member countries. We provided a thorough analysis of different aspects of the COVID-19 third wave across different countries and compared the performance of ML algorithms like Linear Regression, Polynomial Regression, KNN Regression, and Time Series Forecasting to make effective predictions utilizing two years of data. Our findings show that COVID-19 has affected SAARC countries in different ways, depending on their population, healthcare system, pandemic management, and vaccination rate. This study can be helpful in the future to forecast the severity of virus spreading based on statistical data, which is crucial to adopting effective strategies.