Using Different Methodologies of Data Science to Find Comparison Between Them for Cyber-Security

Abstract

The main objective of this paper is that we  have to find out which methodology is effective for Data  Science for the cyber security problem. First of all, we  discuss in the modern world, that data science is one form  of topic where research spans many academic fields. It  consists of scientific methods, procedures, formulas, and  systems to gather information and work on that subject.  When data sciences gather and store big data, analytical  approaches can be used on cyber-security solutions. With  the aid of a mathematical model, machine learning and big  data analysis approaches can be used to manage the effects  of threats. Huge amounts of data are the foundation of  existing cyber-security solutions since more data allows  for more accurate analysis. In data science, it is necessary  to employ data analysis to resolve issues and provide  answers to protect people from cybercrime projects. In this  article, we compare the CRISP-DM, KDD process, and  FMDS data science methodologies with their strong and  weak points.