Predictive Healthcare Analysis of Pakistan’s COVID-19 Pandemic Using Data Mining and Time Series Modelling

Abstract

The novel coronavirus (COVID-19) has significantly spread worldwide and has come up with new challenges to the research community. This forced many affected countries to take stringent measures such as complete lockdown, shutting down businesses and trade, and travel restrictions, which has had a tremendous economic impact. Pakistan has also faced five waves of the deadly coronavirus. Therefore, having knowledge and foresight about how a country can contain the spread of COVID-19 will be of paramount importance to the government, policymakers, business partners, and entrepreneurs. In order to forecast the COVID-19 pandemic's spread, we apply AI-based forecasting models such as time series ARIMA, LSTM, fb Prophet, and VAR. These methods aid in informing public health authorities and policymakers' decisions about how to combat the pandemic. This paper demonstrates the promising potential of the time series model in forecasting COVID-19 cases and highlights the superior performance of the time series compared to the LSTM.