Analisis Klasifikasi Hewan Menggunakan Metode K-Nearest Neighbor, Decision Tree, dan Naïve Bayes

Abstract

Animal classification is an important topic in biology and conservation science, appropriate data analysis methods can help in identifying, classifying, and understanding animal characteristics. This research aims to analyze and compare various animal classification methods using the K-Nearest Neighbor, Decision Tree, and Naïve Bayes methods by implementing them in the Orange Data Mining environment. This study uses a dataset that includes a wide range of biological, morphological, and behavioral attributes of animals. Through the implementation of the orange tools, three different classification methods were developed and evaluated based on their performance in classifying animals into groups according to their characteristics. The research results show that the performance of the K-Nearest Neighbor method is superior to the others. From 101 data tested using the K-Nearest Neighbor method, an accuracy value of 94.1% was obtained. Comparative analysis reveals differences in accuracy and predictive ability between K-Nearest Neighbor, Decision Tree, and Naïve Bayes. These results provide insight into the effectiveness of each method in the context of animal classification and can potentially serve as a basis for selecting appropriate methods in biological research, conservation, or other animal science studies. This research enriches understanding of orange tools in the context of biology and animal science.