Penerapan Naïve Bayes Classifier, Support Vector Machine, dan Decision Tree untuk Meningkatkan Deteksi Ancaman Keamanan Jaringan

Ahmad Zy (Universitas Pelita Bangsa, Bekasi)
Ananto Tri Sasongko (Universitas Pelita Bangsa, Bekasi)
Antika Zahrotul Kamalia (Universitas Pelita Bangsa, Bekasi)

KLIK: Kajian Ilmiah Informatika dan Komputer
Vol. 4 No. 1 (2023): Agustus 2023

This research aims to implement three machine learning algorithms, namely Naïve Bayes Classifier, Support Vector Machine (SVM), and Decision Tree, to enhance network security threat detection. The study utilizes data from multiple sources to train the machine learning models and evaluate their performance in detecting network security threats such as malware, ransomware, and spyware. The research results indicate that all three machine learning algorithms can improve the effectiveness of network security threat detection, surpassing conventional methods in terms of accuracy. Decision Tree yields the best results with a precision of 0.98, , followed by SVM with a precision of 90%, While Naïve Bayes Classifier a precision of 0.86.