Analysis of Nigeria’s COVID-19 Data using Time Series and Maching Learning Models: Imperatives for Actions into Possible Future Pandemic

An analysis of the daily cases of the COVID-19 pandemic in Nigeria was carried out in this paper using Time Series and Machine Learning models. The goal was to examine the long-term trend of the daily cases and based on that, gain insight on the trend that a possible future pandemic of similar features might take, in order to inform decision-making. The Autoregressive Integrated Moving Average (ARIMA) Time Series model based on the Box-Jenkins methodology and the Prophet Machine Learning model developed by Facebook were used to model the daily cases for the period 1st January to 31st December 2021. Both models were used to forecast future values of the daily cases and the efficiency of both models in doing the forecast was assessed to determine the one that is more suitable. The study in general provides us with a hint on how statistical Time Series and Machine Learning models can be applied in observing and understanding patterns present in real-life situations.