Enhancing Email Spam Filter's Accuracy Using Machine Learning

Abstract

In today's world, practically everyone uses emails on a regular basis. In our proposed research, we offer a machine learning-based technique for improving the accuracy of email spam filters. Traditional rule-based filters have become less effective as the number of spam emails has increased tremendously. Machine learning methods, particularly supervised learning, are often used to train models to determine if an email is spam or not. To achieve more accurate results when categorizing email spam, we need to build a simple and uncomplicated machine learning model. We chose the Naive Bayes strategy for our model since it is faster and more accurate than the rest of the algorithms. The recommended solution may be integrated into existing email systems to improve spam filtering capability. This review paper presents an outline of the machine learning model that we have proposed.