Comparison of Accuracy Prediction of Medical Insurance Using Decision Tree with K-Nearest Neighbour

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