<![CDATA[Rainfall refers to the amount of rain that falls over a specific period and is measured on a flat surface that does not absorb or channel the water. Rainfall is classified into six categories: cloudy, light rain, moderate rain, heavy rain, very heavy rain, and extreme rain. The objective of this study is to compare several classification methods in data mining, namely Decision Tree, Naïve Bayes, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) to determine the method with the highest accuracy for classifying rainfall in Malang Regency. To achieve this objective, the procedure used refers to CRISP-DM, which is a methodology for planning data mining projects. The data used in this study were obtained from NASA and consist of daily records collected from June 1, 2019, to June 1, 2025. The total number of observations in this study is 2,193. Data mining classification was employed to identify patterns and similarities in rainfall characteristics in the area. Based on the analysis results, the KNN method demonstrated the best performance with an accuracy of 87.3% and is therefore recommended as the most effective method for rainfall classification in Malang Regency.]]>
Copyrights © 2026
