KOMPARASI ALGORITMA DECISION TREE, NAIVE BAYES DAN K-NEAREST NEIGHBOR UNTUK MENENTUKAN KUALITAS UDARA DI PROVINSI DKI JAKARTA

Abstract

Air quality in DKI Jakarta Province refers to the state and cleanliness of the air in the area at a given time. The type and concentration of air pollutants are among the indicators used to assess air quality. DKI Jakarta's air pollution is severe, causing respiratory irritation, respiratory illnesses, and long-term health issues such as cardiovascular disease and lung cancer. Air pollution can also harm the environment by limiting visibility and harming ecosystems. The problem with the research is that no appropriate and relevant features for predicting air quality were used. The goal of this study is to identify and compare algorithms with the highest accuracy between decision trees. In determining air quality, naive Bayes and k-nearest neighbor are used. According to the findings of the K-5fold evaluation process performed with the RapidMiner tool, the accuracy of the Decision Tree algorithm was 95.89%, the accuracy of the Nave Bayes algorithm was 93.15%, and the accuracy of the K-NN algorithm was 91.78%. Based on these findings, the decision tree method has the greatest or best accuracy when compared to the Nave Bayes and K-NN algorithms.