Machine Learning Algorithm Based Email Spam Detection
N. Bhavana, Avulapalli Sowmya · 2025
Email has emerged as the main channel for both personal and professional interaction due to the quick expansion of digital communication. However, because email is so widely used, there is an increase in spam communications, which can be anything from malicious phishing attempts to innocuous adverts. In addition to filling consumers' inboxes, these spam emails present serious security risks. Conventional rule-based spam filters have not been able to keep up with the changing nature of spam. Because machine learning (ML) algorithms can learn from data and get better over time, they are increasingly being incorporated into spam detection systems. In this paper, a variety of machine learning algorithms, such as Random Forest, Support Vector Machine (SVM), and Naive Bayes, are used to detect email spam. Using a publically accessible dataset, we assess these models on the basis of accuracy, precision, recall, and F1-score. According to our findings, machine learning models—in particular, ensemble approaches—provide reliable and expandable spam detection systems.