COMPARISON OF K-NEAREST NEIGHBOR AND NAÏVE BAYES CLASSIFICATION METHODS FOR STATUS OF TODDLER NUTRITION DATA AT BAQA SAMARINDA SEBERANG COMMUNITY HEALTH CENTER

Abstract

Classification is a job of assessing data objects to put them into a certain class from a number of available classes. The naïve Bayes method is a statistical classification that can be used to estimate the probability of membership in a class. Meanwhile, the K-Nearest Neighbor (K-NN) method is a supervised method used for classification. The aim of this research is to obtain classification results of the nutritional status of toddlers at the Baqa Samarinda Seberang Community Health Center in 2022 using the naïve Bayes algorithm and the K-NN algorithm. Based on the calculation results for classification of the nutritional status of toddlers at the Baqa Samarinda Seberang Community Health Center using accuracy calculations and confusion matrices, the highest accuracy was obtained using the naïve Bayes method of 82.15% and a Press's Q value of 168 with a training data proportion of 90%: testing data of 10%. Meanwhile, the results of accuracy calculations and the confusion matrix obtained the highest accuracy in the K-NN method of 90.57% at values 3-NN, 5-NN, 7-NN, 9-NN and Press's Q value of 187.65 with a training data proportion of 90% and testing data 10%. From the results of this analysis, it was concluded that the K-NN method worked better than the naïve Bayes method in classifying the nutritional status of toddlers at the Baqa Samarinda Seberang Community Health Center.