The main aim of this work is to measure and compare the accuracy prediction of medical insurance using a Decision tree with the K-nearest neighbor algorithm. Supervised Machine learning Techniques with innovative Decision Trees (N = 50) and K Nearest Neighbour (KNN) (N = 50) are performed. In this study, 100 photos were utilized, 80% of them being trained and 20% being tested, and the sample size for two groups was computed using G power with a pretest power of 0.8. Compared to Decision Tree and statistical analysis using SPSS software, 100 photos were utilized for group 1 (K-Nearest Neighbour). K-Nearest Neighbour has a mean accuracy of 87.410.224, whereas Decision Tree achieves an accuracy of 82.470.290, with a significant value of 0.297. Based on the execution analysis, the K-Nearest Neighbour approach outperforms the Decision Tree algorithm in terms of accuracy.