Analisis Perbandingan Kinerja Algoritma Klasifikasi Data Menggunakan Metode K-NN, Naive Bayes, dan Decision Tree pada Dataset UCI Iris

Octavianto, Muhammad Dicky Azhary
Subtari, Tata

MEANS (Media Informasi Analisa dan Sistem)
Volume 10 Nomor 1

Data classification is one of the important techniques in data mining and machine learning, which is widely used to group data into certain classes. This study aims to analyze and compare the performance of three classification algorithms, namely K-Nearest Neighbor (K-NN), Naive Bayes, and Decision Tree, in classifying Iris data from the UCI Machine Learning Repository. This dataset consists of 150 data with four feature attributes and three target classes. Testing was carried out using the cross-validation method with a k-fold approach of 10 folds. The results of the performance evaluation were measured using the metrics of accuracy, precision, recall, and f1-score. Based on the test results, the K-NN algorithm showed the highest accuracy rate of 96.67%, followed by Decision Tree at 95.33%, and Naive Bayes at 94.00%. These findings indicate that choosing the right classification algorithm can affect the success rate in the data classification process.