OPTIMASI DETEKSI SITUS PHISHING MENGGUNAKAN METODE ENSEMBLE VOTING BERBASIS MODEL RANDOM FOREST, LOGISTIC REGRESSION, DAN SVM

Robani Amin, Muhammad Iqbal Fikri (2025) OPTIMASI DETEKSI SITUS PHISHING MENGGUNAKAN METODE ENSEMBLE VOTING BERBASIS MODEL RANDOM FOREST, LOGISTIC REGRESSION, DAN SVM. Undergraduate thesis, Universitas Pembangunan Nasional Veteran Jawa Timur.

	Text (Cover) Cover.pdf Download (1MB)
	Text (BAB I) Bab I.pdf Download (243kB)
	Text (BAB II) Bab II.pdf Restricted to Repository staff only until 12 June 2028. Download (656kB)
	Text (BAB III) Bab III.pdf Restricted to Repository staff only until 12 June 2028. Download (909kB)
	Text (BAB IV) Bab IV.pdf Restricted to Repository staff only until 12 June 2028. Download (2MB)
	Text (BAB V) Bab V.pdf Download (210kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf Download (182kB)

Abstract

Phishing attacks are among the most common and dangerous cyber threats, as they can lead to the theft of personal information and financial losses. This study aims to develop a phishing website detection system using the Ensemble Weighted Voting method, which combines three classification algorithms: Logistic Regression, Random Forest, and Support Vector Machine (SVM). Each algorithm contributes uniquely based on its individual strengths in processing data.The initial stage involves preprocessing, including data cleaning, standardization, and feature selection using Random Forest, followed by hyperparameter optimization using the GridSearchCV technique to obtain the best parameters for each model. Each model is then evaluated through several testing scenarios involving combinations of hyperparameter tuning and feature selection. These scenarios are assessed using performance metrics such as accuracy, precision, recall, F1-score, and ROC – AUC .Evaluation results show that the Random Forest model achieved the highest accuracy of 99.33% after optimization. Meanwhile, the Ensemble Weighted Voting method provided the best overall performance, with a precision of 98.97%, recall of 98.98%, F1-score of 98.97%, and an almost perfect ROC – AUC value. This research demonstrates that the ensemble weighted voting method, when combining the right models, can significantly enhance the accuracy of phishing detection systems and has the potential to be applied in strengthening cybersecurity at both individual and organizational levels.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Diyasa, I Gede Susrama Mas	NIDN197006192021211009	igusrama.if@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id

Subjects:

Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Muhammad Iqbal Fikri Robani Amin

Date Deposited:

12 Jun 2025 08:53

Last Modified:

17 Jun 2025 04:04

URI:

https://repository.upnjatim.ac.id/id/eprint/37264