Phishing E-mail Detection Using Machine Learning

The use of the internet has widened the possibilities for humans to interact. At the same time, it has become a tool and media for spamming and fraudulent activities. Cybercrimes include identity theft, phishing, ransomware, DDoS, and many others. The rate of frauding people through text SMS and email is increasing day by day with high-tech tools handed over to common citizens. It is challenging to identify such malicious and skeptical emails. Phishing email detection using machine learning implements various machine learning techniques on four different datasets for spam email detection. This paper includes all the steps and information sources utilized for the detection of spammed information. The developed framework uses a huge dataset and performs featurization, fitting, training, and testing. This paper observes the remarkable precision in classifying emails. From experimented data and results Random Forest was found to be the optimal algorithm. The algorithm showed a precision of 100% and an accuracy to be 99%. Contributing to real-life email security applications, these machine learning models are trained and fine-tuned to handle nonlinear relationships.