In recent times an unhealthy lifestyle has led to rising in various heart conditions. Lots of people are losing their lives because of this. It would be really great to have the technology or a system that can collect data and predict and monitor heart conditions. So that person's life can be saved before it's too late. Accurate heart condition predictions are not an easy task. Data Science and AI can play a huge and crucial role in processing huge amounts of healthcare data. There are various machine learning algorithms available to process and predict the result. It is very important to choose the right algorithm so that the task can be performed efficiently. This ‘Seminar Work’ makes use of a heart dataset available in the UCI machine learning repository. The proposed work aims to predict the chance of heart attack and classifies patients' risk levels. We have implemented various machine learning algorithms such as Decision Tree, Logistic Regression, Random Forest, Naive Bayes. In this report, we have comparatively studied and analyzed the above algorithms. We compared the performance for all of them and tried to choose the best-suited algorithms for our task. The results of our test concluded that Random forest is the best-suited algorithm for our task. It has achieved the highest accuracy of 90.16% compared to other machine learning algorithms.