Ensemble Learning based Classification of UNSW-NB15 dataset using Exploratory Data Analysis
Neha Vaishnavi Sharma, Narendra Singh Yadav · 2021
Recent advancements in machine learning have made it a tool of choice for different classification and analytical problems. Over the last decade, data has increased exponentially in networking domains, so naturally, there is a need to understand this data to get useful insights. This paper deals with a critical field of computer networking: network security and the possibilities of machine learning automation in this field. We will be doing exploratory data analysis on the benchmark UNSW-NB15 dataset. This dataset is a modern substitute to the outdated KDD'99 dataset as it has greater uniformity of pattern distribution. We will also implement several ensemble algorithms like Random forest, Extra trees, AdaBoost and XGBoost to derive insights from the data and make useful predictions. We calculated all the standard evaluation parameters for a comparative analysis among all the classifiers used. This analysis gives knowledge, investigate difficulties, and future opportunities to propel machine learning in networking. Along these lines, it is a beneficial contribution to enhance the understanding of machine learning for networking, pushing the limits of automation using machine learning for better network management. This paper can give a basic understanding of the data analytics in terms of security using Machine Learning techniques.