The growth of technology and the impact of industrial activities on the earth have an influence on environmental changes, including changes that are felt are a decrease in air quality or air pollution which has an impact on the health of the human body. Based on this, this research aims to produce a model for solving air quality classification problems based on parameter indicators. A comparative evaluation was also carried out on the classification of the K-Nearest Neighbor and Naive Bayes algorithm methods on the air quality dataset in South Tangerang in 2022. At the same ratio in the classification process, the K-Nearest Neighbor algorithm got an accuracy value of 94.44% and the Naive Bayes algorithm got an accuracy value of 94.44%. Accuracy value 86.11%. From the results of testing the data, it can be concluded that the K-Nearest Neighbor algorithm has high accuracy compared to the Naive Bayes algorithm in air level classification.