Recently, the Corona pandemic wave has lessened, and most people got vaccinated, but the road to reach this status was rough and had some trials and errors. After going through several challenges with the pandemic during the past two years, a lot of related datasets have been created to help researchers. In these datasets, the choice of stringency level index has played a key role in controlling the spread of the pandemic as well as the associated number of deaths. Machine learning techniques have been deployed to relate policy makers’ choices of stringency index level to different related outcomes such as the number of infected cases as well as the number of associated death cases. In this proposed research, the problem is approached from a different angle where the designed machine learning models will predict the stringency index level based on a few attributes such as infected cases and death cases. Different supervised machine learning techniques have been used in the designed models, and the achieved accuracies reached 94.84%. In addition, an important note for policy makers wasrevealedto take into consideration while applying the designed prediction models to make their decision choices more robust. It is believed that the discovered lag noted in public response to the applied stringency measures should be amended to achieve better accurate results and therefore a solution for policy makershave been suggested. Based on the findings of our proposed research, it is believed that policy makers could benefit from the designed prediction models as well as the lag avoidance suggested approach to have more control on similar future pandemics.

Corona Pandemic Stringency Index Supervised Machine Learning Techniques