<![CDATA[The development of diabetes continues to increase accompanied by an increase in unhealthy lifestyles with a high number of cases, making diabetes need to be continuously researched and developed to obtain useful information in terms of research related to diabetes. This study aims to predict diabetes using the K-Nearest Neighbor Algorithm and make a simulation of checking the disease and test the quality of the K-Nearest Neighbor Algorithm for diabetes and make comparisons with the Naïve Bayes algorithm. The K-Nearest Neighbor algorithm is the method used in this study because it has the advantage of being able to train data that is fast, simple, and easy to learn. The way this algorithm works is by calculating the distance between each row of training data and test data based on a predetermined K value. In the process of using the K-Nearest Neighbor, there is a Z-Score normalization stage which is used to adjust the values for each attribute of diabetes symptoms so that they have a range of values that are not too far away. Based on the results of the research and testing of the K-Nearest Neighbor that has been carried out, an accuracy of 97.12% is obtained and the Area Under Curve value is 0.872 which is included in the good classification category and these results have a greater accuracy value compared to previous studies on the same disease, namely Diabetes with the Naïve Bayes algorithm which produces the most optimal accuracy of 87.69%.]]>
Copyrights © 2023
