Enhancing Phishing Website Detection with Machine Learning Algorithms

This paper examines the impact of feature selection on phishing website detection using machine learning techniques. We utilize the UCI Phishing Website dataset, which consists of 11,055 instances and 30 features with no missing values. Our results show that the random forest outperforms logistic regression, achieving an accuracy of 97.11%. By analyzing feature importance, we optimize the model by removing detrimental features, further improving accuracy to 97.74%. This study highlights the effectiveness of the random forest in phishing detection and underscores the importance of feature selection in enhancing model performance.