In living organisms, the heart plays an important function. Diagnosis and prediction of heart diseases necessitates greater precision, perfection, and accuracy because even a minor error will result in fatigue or death. There are multiple death cases related to the heart, and the number is growing rapidly day by day. The scope of this study is restricted to discovering associations in CHD data using three super- vised learning techniques: Logistic Regression, K-Nearest Neighbour, and Random Forest, in order to improve the prediction rate. As a result, this paper conducts a comparative analysis of the results of various machine learning algorithms. The trial results verify that Logistic Regression algorithm has achieved the highest accuracy of 89% com- pared to other ML algorithmsimplemented. Keywords: Machine Learning, Logistic Regression, K-Nearest Neighbour, Random Forest, Python, Heart Disease, Prediction model, Healthcare