Deep Cyber: Using Big Data Distributed Machine Learning for Fraud Detection and Risk Assessment in Large Financial Institutions
This project focuses on the design and development of a Big Data Deep Learning Framework for Cyber Threats.
Over the past decade, rapid developments in Machine Learning, Data Science and software/hardware technology have unlocked a considerable potential in satisfactorily addressing computational and “intelligent” tasks to a level that was previously thought to be unattainable. Such capabilities have benefited, sometimes greatly, a variety of application domains with image recognition/annotation via deep learning being, perhaps, an egregious example.
The realm of the financial industry presents a host of opportunities for applying some of the aforementioned breakthroughs. For example, a banking institution may be preoccupied, among many other concerns, by customer satisfaction and retention, marketing financial products to its customer base and protecting itself and its customers from a wide spectrum of fraudulent activities, especially now, in the era of online banking. In what follows, we provide an indicative example of such a challenge, namely credit card fraud, accompanied with a state-of-the-art approach in addressing it.
With the increase of credit card usage, the volume of credit card misuse also has significantly increased, which may cause appreciable financial losses for both credit card holders and financial organizations issuing credit cards. As a result, financial organizations are working hard on developing and deploying credit card fraud detection methods, in order to adapt to ever-evolving, increasingly sophisticated defrauding strategies and identifying illicit transactions as quickly as possible to protect themselves and their customers. Compounding on the complex nature of such adverse strategies, credit card fraudulent activities are rare events compared to the number of legitimate transactions. Hence, the challenge to develop fraud detection that are accurate and efficient is substantially intensified and, as a consequence, fraud detection has lately become a very active area of research.
- Dr. Ivan Garibay
- Dr. Georgios Anagnostopoulos
Florida Institute of Technology