PERFORMANCE EVALUATION OF VARIOUS MACHINE LEARNING MODEL FOR PHISHING DETECTION
Abstract
This project investigated machine learning models for phishing detection in depth, beginning with data loading and visualization and ending with the implementation and comparison of different algorithms. The study used decision trees, Random Forest, Multilayer Perceptron, XGBoost, and SVM to meticulously navigate through stages of data preprocessing and model optimization. The results showed that XGBoost was the most effective model, with superior training and testing accuracies. Future work should focus on feature engineering, advanced hyperparameter tuning, and ensemble methods, with an emphasis on model explainability and continuous monitoring for real-world deployment. This project contributes to the changing landscape of cybersecurity by shedding light on effective phishing detection strategies and laying the groundwork for ongoing model refinement and adaptation.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.