Paper Title
Predicting Fraudulent URLs through Machine Learning

Abstract
Machine Learning has proved to be pivotal and efficient in predicting relative outcomes of events and helping people take more secure and informed decisions. Such decisions have been important in almost every field that has a relation with information. One such field is CyberSecurity, and through this project, we will be focusing on Predicting the type of Uniform Resource Locator’s (URL) that tend to be fraudulent in nature and can prove to be harmful in the near future as everything we know is going digital. This will be done by comparing Machine Learning techniques such as Random Forest, Decision Tree, Multi-Layer Perceptron, Logistic Regression, and XGboost. Furthermore, the features of a URL will be explained through visualizations and how they contribute to predicting fraudulent URLs. Keywords - Cyber Security, Machine Learning and Phishing etc.