Optimasi Gaussian Naïve Bayes dengan Hyperparameter Tuning dan Univariate Feature Selection dalam Prediksi Cuaca

Abstract

The importance of conducting weather prediction research is due to the significant influence of weather changes on daily life. The purpose of this study is to apply an optimal machine-learning classification method for weather prediction. The method used is the Gaussian Naïve Bayes model, which has been optimized using Univariate Feature Selection ANOVA-f test and Hyperparameter Tuning GridsearchCV techniques. The data used consists of 6454 daily weather data in Palembang City. There are 5 tests on the Gaussian Naïve Bayes model before and after optimization. The research results show that the optimization of the model successfully improves the performance in weather prediction. The highest accuracy result after optimization reaches 98.33% with 644 test data, an improvement from the pre-optimization accuracy of only 96.95%. Before optimization, the predictions for weather conditions such as sunny, cloudy/rainy, light rain, and heavy rain match the actual data. However, there were 20 prediction errors when dealing with data that should represent very heavy rain conditions. After optimization, the number of prediction errors for the very heavy rain data was reduced to seven. The optimization approach used in this research helps find the most suitable parameter combinations and eliminates irrelevant features, allowing the model to consider only significant features in weather p