Drug repurposing is an ancient method to deal with a pandemic or any other disease that is unknown and yet does not have any cure, in these scenarios, most of the time doctors treat the symptoms with existing approved and tested drugs. There are a couple of benefits of using existing drugs, existing drugs are already approved and tested, known effects and side effects, and time-saving special in pandemic scenarios. The machine learning predictive models approach in drug repurposing is groundbreaking, The pandemic time is full of chaos and people rush to save a life, “time is of the essence when it comes to saving lives.” The drug repurposing method is already time-saving but it also takes time example first case of COVID-19 reported in December 2019 and Remdesivir got EUA in May 2020, 5 months just to use the existing drug, this 5 months could turn into seconds when we do drug repurposing using machine learning. The review discusses machining learning algorithms, especially supervised learning algorithms that Support Vector Machine, Random Forest, Decision Tree, K-Nearest Neighbors (KNN), and Naive Bayes used in drug repurposing, and their results. The review discusses machining learning algorithms, especially supervised learning algorithms and common classification algorithms used in drug repurposing, and their results. The results and conclusion of this study indicate that the Random Forest model stands out as the most effective method. However, compared to Random Forest, other classification algorithms such as Decision Tree and Naive Bayes did not perform as well for this particular application.