How to use big data to combat fraud

As banks and financial institutions grow significantly in size and revenue, they also experience phenomenal risk in the form of fraud. There has been a recent increase in the momentum and intensity of fraudulent activity challenging experts and participants alike in the payments industry, exposing the organizations involved to financial losses. Constant vigilance and fraud deterrence through technology is the key to the protection of the assets of the customers and the organization involved.

This necessitates employing dynamic profiling of accounts using Big Data technology to proactively prevent fraud attacks. Also, due to the high volumes of data, a robust framework is essential for effective risk profiling.

These four analytical layers act as foundation for a robust framework:

• Ingestion Layer: imports data from multiple sources and formats it in a standardized format to be used across the framework
• Management Layer: performs a set of alterations and rules on the data ingested; this layer is also responsible for the data set manipulation, as well as the quality, integrity, and security of the data
• Analytics Layer: builds data mining rules or algorithms using the techniques of predictive and descriptive analytics
• Real-time Stream Processing Layer: generates further action triggers or alerts based on the application of decision analytics or decision engineering techniques

Decision engineering based on machine learning techniques can be used for generating triggers or alerts, making the system robust and dynamic, and thereby creating dynamic risk profiles for accounts.

Though this framework helps an organization create dynamic risk profiles for accounts, its success largely depends on buy-in and involvement from senior management, high level of usability, and the availability and integrity of data and sources used. At the same time, the technology framework should be designed to be sensitive and flexible enough to adapt to new regulations, changes to existing law, and ever-changing endeavors of fraudsters.

How does your organization leverage Big Data to combat financial fraud?

This article is published in collaboration with Tata Consultancy Services. Publication does not imply endorsement of views by the World Economic Forum.

To keep up with Forum:Agenda subscribe to our weekly newsletter.

Author: Kothai M is Domain consultant as a part of the Delivery Excellence and Risk Management – Process Risk Review.

Image: An illustration picture shows a projection of binary code on a man holding a laptop computer, in an office in Warsaw June 24, 2013. REUTERS/Kacper Pempel.