PREDICTION OF AIR QUALITY INDEX USING DECISION TREE WITH DISCRETIZATION

Ning Eliyati (Departement of Mathematics, Faculty of Mathematics and Natural Science, Universitas of Sriwijaya, Inderalaya, Indonesia)
Mauizzatil Rahmayani (Departement of Mathematics, Faculty of Mathematics and Natural Science, Universitas of Sriwijaya, Inderalaya, Indonesia)
Shohif Wijaya (Departement of Mathematics, Faculty of Mathematics and Natural Science, Universitas of Sriwijaya, Inderalaya, Indonesia)
Des Alwine Zayanti (Departement of Mathematics, Faculty of Mathematics and Natural Science, Universitas of Sriwijaya, Inderalaya, Indonesia)
Endang Sri Kresnawati (Departement of Mathematics, Faculty of Mathematics and Natural Science, Universitas of Sriwijaya, Inderalaya, Indonesia)
Yulia Resti (Departement of Mathematics, Faculty of Mathematics and Natural Science, Universitas of Sriwijaya, Inderalaya, Indonesia)

Indonesian Journal of Engineering and Science (IJES)
Vol. 3 No. 3 (2022): Table of Content

Air quality is indicated by the Air Quality Index (AQI). Prediction or classification of AQI is an important research issue because it can impact many factors, such as the environment, health, transportation, agriculture, plantations, tourism, and education. The purpose of this study is to predict AQI using a decision tree. The results of calculating the performance of the decision tree method that implements the discretization technique show that this method is very good at predicting air quality, as indicated in particular by the Average Accuracy value of 99.05%, Macro Precision of 78.59%, and Macro Recall of 77.46%.