Machine Learning-Based Spam Detection: A CRISP-DM Approach for Enhanced Email Security
Mohan Bansal, Ramesh Saha · 2024
Emails are becoming the most significant official communication channel in the current digital world. The majority of people have multiple email addresses and often use them. Spam emails have become a serious danger element for consumers as a result. This obnoxious mass email poses security risks. The aim of this paper is to lower these hazards by using machine learning to detect spam. The dataset, which includes the records of spam emails, was acquired from Kaggle. To identify the most successful model, the performance of three models has been examined and contrasted. The entire process of the technique has been organized using a step-by-step Crisp-DM method. Preprocessing and exploratory data analysis are included in the study to obtain important insights into the sender information, pertinent attributes, and email content. The objective of this study is to develop a robust system classification that can accurately identify and filter spam emails from legitimate ones. Various types of machine learning models, such as decision tree, logistic regression and random forest are evaluated.