Big Data Applications in Banking: A Bibliometric Analysis of Research Trends (2020–2026)

Abstract

The landscape of the banking industry has undergone a radical transformation post-COVID-19, shifting from reactive digitization to algorithmic financial intelligence. This study presents a comprehensive bibliometric analysis of big data applications in banking from 2020 to 2026. Utilizing a dataset of 479 open-access articles retrieved from the Scopus database, we map the intellectual structure, social networks, and thematic evolution of this domain using RStudio’s bibliometrix package and VOSviewer. The temporal analysis reveals a distinct transition: while the 2020-2022 period focused on digital banking adaptation and basic fintech integration, the 2023-2026 period is heavily dominated by advanced machine learning, anomaly detection, ESG (Environmental, Social, and Governance) integration, and financial inclusion. Cooccurrence analysis identifies five major thematic clusters, positioning machine learning and deep learning as core "Motor Themes". The global research landscape is led by advanced economies with strong fintech ecosystems, maintaining an international collaboration rate of 29.23%. This paper provides critical evolutionary insights and outlines strategic research fronts for future academic and industry exploration.