Classification model for Neptune attacks in network activity.

This project focuses on creating a Machine Learning model to classify network activity as either normal or indicative of a Neptune attack (SYN flood attack). Using a training dataset of 86,845 records with labels, the model is trained to identify these attacks. Data preprocessing steps include addressing missing values, encoding categorical variables, and scaling features. A Random Forest Classifier is employed, with its hyperparameters fine-tuned via Grid Search, and its performance measured using F1 score and accuracy. The refined model is then applied to predict attack instances on a test dataset of 21,712 records, with predictions formatted for submission as required.