Network Intrusion Detection System

A course project for Artificial Intelligence

---

Source Code

Description

Given a dataset of network traffic records, this projects aims to develop a Network Intrusion Detection System capable of analyzing network traffic records to classify them as normal or malicious, as well as identifying the specific category of attacks if present.

---

About

This is a course project for my Artificial Intelligence class. In this project, I:

• Processed the dataset, including dataset splitting, imputing missing values, factoring categorical variables, and removing outliers.
• Selected from 47 features to build a classification model using Random Forest, to predict both binary and categorical labels (is attack or not, and attack category).
• Fine-tuned the model with halving random search.

---