PERBANDINGAN DETEKSI WEB PHISHING DENGAN FITUR MENGGUNAKAN SVM, RANDOM FOREST, DAN GRADIENT BOOSTING CLASSIFIER

Linda Khoirul Inayah, NIM.: 22206052006 (2024) PERBANDINGAN DETEKSI WEB PHISHING DENGAN FITUR MENGGUNAKAN SVM, RANDOM FOREST, DAN GRADIENT BOOSTING CLASSIFIER. Masters thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (PERBANDINGAN DETEKSI WEB PHISHING DENGAN FITUR MENGGUNAKAN SVM, RANDOM FOREST, DAN GRADIENT BOOSTING CLASSIFIER) 22206052006_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (2MB) | Preview
	Text (PERBANDINGAN DETEKSI WEB PHISHING DENGAN FITUR MENGGUNAKAN SVM, RANDOM FOREST, DAN GRADIENT BOOSTING CLASSIFIER) 22206052006_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

In this era, humans are increasingly dependent on technology and the internet, which caused in increase in cybercrime cases, one of which is phishing. This research examines web phishing detection using three machine learning algorithms, namely Support Vector Machine (SVM), Random Forest, and Gradient Boosting Classifier. This research aims to compare the accuracy and effectiveness of the three algorithms in detecting phishing websites. The data consists of 11,054 URLs with 31 features, and the data is divided using the Holdout method with a ratio of 20:80 between test data and training data. The research results show that the Gradient Boosting Classifier algorithm achieved the highest accuracy of 97.4%, followed by Random Forest (96.7%) and SVM (96.4%). Apart from that, the Gradient Boosting Classifier also shows the highest F1 value, namely 97.7%, and recall and precision of 99.4% and 98.6% respectively. This research indicates that the Gradient Boosting Classifier is the most effective algorithm for web phishing detection, with the best performance in terms of accuracy, precision and recall.

Share this knowledge with your friends :

Actions (login required)

View Item