With the enormous enhancement of diseases in medical and the other communities of healthcare, it is extremely important to have an analysis of the heart diseases at the early stages. Since, nowadays it is very important to detect the diseases and lessen the death of patients at early stages. Every person has different values of cholesterol, blood pressure and many more that are linked with heart disease prediction. But it has scientifically proven that the normal person blood pressure is counted to be 120/90 along with this the pulse rate and the cholesterol value is 72. In this paper, the various “machine learning algorithms” are explained that include Support Vector Machine, Decision tree, neural network and many more are explained so that complete description can be provided. Along with this, the entire description of the heart disease has been provided that depicts about the need for the topic to be selected. There are some of the issues present in the Data Mining algorithm that are also described in the paper. The ultimate aim is to improve efficiency in different parameters by describing the classification approach for detecting heart disease. The parameters on which the prediction can be done are the age, serum cholesterol, gender, blood pressure, pulse rate. The accuracy and the efficiency in the prediction can be increased only if the number of attributes is more. For the classification of heart disease, the most efficient algorithm is the Support Vector Machine algorithm since it will not only reduce the prediction time but will also improve the efficiency of the algorithm.