CLIENT / STUDENT PROJECT

Email Spam & Malware Classification System

Machine Learning · Email Security

Client · Student project Available

Machine-learning classification project analysing email data with TF-IDF and multiple supervised learning algorithms.

Pythonpandasscikit-learnXGBoostTF-IDF

Email Spam & Malware Classification System project preview

This project explores machine-learning techniques for classifying email content using text-processing and supervised-learning methods.

A dataset containing more than 33,000 records was processed into machine-readable features and used to train and compare multiple classification approaches.

CHALLENGE

Spam and malicious email can appear in many forms, making simple keyword rules unreliable.

Raw text also cannot be passed directly to conventional machine-learning models, so messages first need to be cleaned and transformed into useful numerical features.

SOLUTION

The workflow uses Python and pandas for data handling and TF-IDF for text vectorisation.

Multiple classifiers were explored, including Naive Bayes, Support Vector Machine, Random Forest and XGBoost, allowing different approaches to be compared on the processed dataset.

OUTCOME

The project produced a complete machine-learning classification workflow covering data preparation, feature extraction, training and prediction.

Final accuracy figures should only be published after rerunning and verifying the final model evaluation.