Comparison of Decision Tree and Naive Bayes in Analysing Weather Monitoring System

Abstract

Weather is an important factor that affects various human activities, including agriculture, transportation, and even education. Uncertainty in weather conditions can disrupt teaching and learning activities, as was the case in Makassar City at the end of 2024 due to extreme weather. To address this challenge, this study developed an Internet of Things (IoT)-based weather monitoring system to monitor weather parameters such as temperature, humidity, and wind speed in real-time, as well as predict future weather conditions. This system is designed to support the learning activities of Batam State Polytechnic students by providing accurate weather information at the campus location that can be accessed anytime and anywhere. To optimize weather prediction accuracy, this study compares the performance of two popular methods in weather data analysis, namely Decision Tree and Naive Bayes. Based on testing and evaluation using accuracy metrics, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), it was found that the Decision Tree method performs better than Naive Bayes in real-time weather monitoring and predicting future weather conditions in the weather monitoring system developed by the authors.