Decision Tree-Based Fraud Detection and Financial Data Protection in Digital Banking

DOI

No DOI

Published In

Volume 5, Issue 3 (2026)

Published Online

September-December 2026

Pages

654-657

Article Type

Original Article

Check for updates

No DOI available for cross-reference

As banking becomes more digital to increase convenience of online transactions, the risk of financial scams increases noticeably because banks now have to store huge amounts of personal and sensitive financial data in their systems. This increases the need for effective fraud detection in order to protect user privacy. Conventional detection methods are not as effective as those that can be enforced using newer technologies. Artificial Intelligence and Machine Learning models can be helpful in stopping potential scams by identifying patterns. The aim of this research paper is to propose a decision tree based machine learning model that can help identify suspicious transactions and terminate them before any significant harm is caused, while also protecting user data. A decision tree algorithm is the most ideal for this scenario since its decision making process is the easiest to interpret compared to other algorithms. The proposed model considers data minimisation, which only provides the required data to the algorithm while maintaining complete confidentiality of sensitive information. This model has not been experimentally tested and hence the degree of its effectiveness may vary under various circumstances. This research paper wishes to evaluate how fraudulent transactions can be detected while still considering the importance of customer data privacy.