<![CDATA[KNN classifier algorithm for developing an automatic classification system in categorizing knn methods. The classification process using the K-Nearest Neighbor (KNN) algorithm was chosen because it is simple and easy to implement. This study aims to determine the characteristics of the choice of contraceptives in Salahutu District, Central Maluku Regency and classify the choice of contraceptives in Salahutu District, Central Maluku Regency using the KNN method. A total of 1393 respondent data as a sample and 11 predictor variables and 1 response variable by calculating the distance between documents in the n-dimensional diagram is Euclidian Distance, the algorithm for classifying is the KNN algorithm, and the method for validating research results uses K-Fold Cross Validation. The results of this research are that the KNN algorithm can classify contraceptive methods with a level of accuracy. Comparison of Balanced Accuracy for each K for comparisons of 90:10%, 80:20% and 70:30% has been carried out with K values of 4, 6, 8, 36, 37, 38, the best performance of the KNN classification model is obtained with a ratio of 90:10% of the KNN model with a value of]]>
Copyrights © 2024
