Data Science for the Next Millennium: A Ubiquitous Review

Abstract

Data science has grown from a set of statistical and computational techniques into a field that brings together different disciplines to turn complex data into useful insights. This review looks at how data science was defined, applied, and studied across different fields from 2018 to 2023. The review followed a structured approach and drew on research identified through several scholarly sources. The initial search found 105 articles in databases and platforms including EBSCO, Taylor & Francis, Wiley, Sage, Emerald, and Google Scholar. After screening, 40 studies were examined in detail. The review considered each study’s purpose, findings, application area, country, analytical tools, and research type. The findings show that data science brings together computer science, statistics, business analysis, engineering, machine learning, automation, and subject-specific knowledge. Education and healthcare were the most common areas of application in the studies reviewed. Researchers used a wide range of methods and tools, including machine learning, artificial intelligence, regression, neural networks, data mining, SQL, Python, R, CRISP-DM, statistical analysis, optimization, and data visualization. Empirical research made up the largest share of the studies, though conceptual papers and reviews also contributed to the field. Overall, the review suggests that successful data science depends on more than algorithms. It also requires reliable data, privacy safeguards, relevant skills, thoughtful interpretation, ethical practice, and a clear understanding of the problem being addressed.