Data Science Methodology

View Sample PDF

Author(s): Matthias Pohl (Otto von Guericke University, Germany), Christian Haertel (Otto von Guericke University, Germany), Daniel Staegemann (Otto von Guericke University, Germany)and Klaus Turowski (Otto von Guericke University, Germany)
Copyright: 2023
Pages: 14
Source title: Encyclopedia of Data Science and Machine Learning
Source Author(s)/Editor(s): John Wang (Montclair State University, USA)
DOI: 10.4018/978-1-7998-9220-5.ch070

Keywords: Data Analysis and Statistics / Information Science Reference / Knowledge Management and Library Science / Machine Learning

Purchase

View Data Science Methodology on the publisher's website for pricing and purchasing information.

Abstract

An overview of common process models for the implementation of data science is presented in this article. Since the development of KDD and CRISP-DM, the central ideas have been examined from broader perspectives, and further frameworks have been created. In addition to the core activities that are conducted in the individual process phases, typical roles and project-supporting artifacts are outlined. In summary, a distinction can be made between four process phases that relate to ideation, data, analysis, and deployment. These phases are considered as a holistic methodology of data science. The overview is an orientation for data scientists and project managers in the preparation and realization of data science projects. However, many challenges need to be overcome to further specify and specialize the processes, which may also lead to new approaches to data science methodology in the future.

The IRMA Community

Research IRM

Data Science Methodology

Purchase

Abstract

Related Content

IRMA Sponsors