Intelligent Detection Engine: Email Phishing Messages Classification Using Machine Learning

This research presents an Intelligent Detection Engine for Email and Social Media Phishing Classification using machine learning techniques. The study focuses on identifying spam and phishing messages by analyzing both content-based and behavioral features extracted from real-time datasets. Multiple supervised machine learning algorithms—including Decision Tree, Random Forest, Support Vector Machine (SVM), and Naïve Bayes—were implemented and evaluated to determine the most effective classification model. A comprehensive data preprocessing pipeline was applied to clean and optimize the dataset, followed by feature selection to improve detection accuracy. Performance was measured using standard metrics such as accuracy, precision, recall, F1-score, and memory efficiency. Experimental results demonstrate that the Random Forest classifier outperforms other models, achieving higher accuracy and robustness in detecting phishing and spam messages. The proposed system provides an efficient and scalable solution for real-time phishing detection, contributing to enhanced cybersecurity mechanisms for email systems and online social networks.