Heart disease is one of the most common diseases suffered by Indonesian people, in 2018 there were 1.5% of people with heart disease according to a doctor's diagnosis. With so many cases that have occurred, this research was conducted with the aim of implementing an algorithm to help classify whether a person has the potential to have heart disease or not. The algorithms that will be used are K-Nearest Neighbor (K-NN) and Naive Bayes Classifier (NBC). The accuracy of the two algorithms will be compared, so that it can be seen which algorithm is better in classifying heart disease. The final results obtained show that the NBC algorithm has a higher accuracy rate of 86.17%, while KNN has a slightly lower accuracy rate of 85.11%. By implementing a data mining algorithm to compare the K-NN and NBC algorithms using the heart disease data set, it can be used to help determine whether a person can be classified as having heart disease or not. And by comparing the accuracy of the two algorithms, it can be seen which algorithm is considered better in handling cases of heart disease classification.