There are many existing fraud detection techniques employed by card issuers and researchers globally. Despite this evolution of several fraud detection techniques, billions of dollars are still lost due to credit/debit card fraud every year. This paper proposes a fraud detection framework that uses online behavioural targeting (OBT) data and device fingerprinting (DF) to improve the efficiency of the fusion approach using Dempster-Shafer theory and Bayesian learning. OBT and DF provide massive insights into our online behaviour and can be used to pinpoint fraudsters as well as know shopping patterns of credit card users. These technologies are able to track and profile Internet users up to the level of what device they are using and what they are most likely to purchase. The paper also presents the theoretical underpinnings of the framework and its application scenarios.
|Number of pages||24|
|Journal||International Journal of Electronic Security and Digital Forensics|
|Publication status||Published - 2019|
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Safety, Risk, Reliability and Quality