A Data-Driven Approach to Anonymizing Customer Personal Information in Banking Systems for Privacy Preservation

Abstract

The rapid growth of digital technologies has accelerated the adoption of online banking and e-commerce services, enabling fast and convenient financial transactions. However, the extensive collection and processing of customer data have introduced significant cybersecurity and privacy risks, particularly the possibility of re-identification by malicious actors. This study proposes a multi-level anonymity analytics framework to enhance the protection of customer personal information in banking systems. The approach focuses on improving data anonymity to reduce the likelihood of privacy breaches while maintaining data usability. In addition, the research implements a k-anonymity-based method to ensure that sensitive information is adequately protected without compromising its value for operational use. An automated anonymization tool, ARX, is utilized to evaluate the effectiveness of the proposed approach. The study demonstrates that increasing the k-anonymity level reduces re-identification risks while preserving data utility. The proposed methodology aims to provide a scalable and efficient solution for privacy preservation and can be applied across sectors such as banking, healthcare, and telecommunications where sensitive personal data is handled.