Credit Card Transaction Data Analytics
Identity verification and fraud prevention have become a thorn in the sides of financial services providers in light of the rise of digital technologies.
With so many avenues for fraud out there, banks and credit societies have increasingly become more exposed to aggressive fraud attacks.
Identity theft, bad faith, and synthetic fraud are difficult to identify and mitigate without affecting good, well-intentioned customers. In many cases forcing financial institutions to go back and forth with customers to determine if fraud is taking place thus slowing and adding friction into the process. It’s a bad situation for everybody.
Bank transaction data (BTD) analytics solutions offer a new opportunity to improve fraud prevention based on granular information backed by strong security logic. Identifying fraud during a credit application – whether somebody wants to get a personal loan, credit card, auto loan or a mortgage – can prevent an identity thief from creating fraudulent accounts and give you more security when opening a line of credit for an existing customer.
How BTD supports fraud prevention
Most fraud prevention systems that use account data to identify if fraud has taken place tend to focus on fairly one-dimensional points of information. For example, the solution might use name matching – ensuring the name of the individual associated with a transaction matches the name of the account holder. This is a solid baseline strategy, but it doesn’t provide any depth in the logic. What’s more, it isn’t helpful in empowering banks and credit societies to assess a customer’s credit situation for a loan, because the limited logic doesn’t stop a person who, for example, used stolen card details to make purchases without being noticed.
What leading BTD analytics systems do is make a multi-level analysis that checks multiple conditions against one another to flag potential cases of fraud. Some of these checks include:
Layered name matching
Providing name-based verification at the transaction at the application and account transaction levels to offer multiple layers of protection. On its own, this method is limited, but as the first line of defense in a more complex solution, it becomes a useful tool. If somebody manages to take over an account and put it in their name, he or she won’t get away with it for long because incoming deposits in the previous account holder’s name will lead to an alert. But this is just the first step in how our system offers protection.
Contact history tracking
When a person changes the personally identifiable information (PII) or banking data associated with an account, it isn’t always a sign of fraud on its own. People make alterations details like addresses, phone numbers, and even names fairly regularly. But when patterns of PII changes don’t align with the account or transaction name matching, there’s a problem. Of course, it may not be an issue at first. Somebody who takes on a new name after marriage may go through a month or two where some payments or deposits are logged in the system with his or her old name. But we track trends over 30, 60 and 90-day periods, providing granular visibility into alignment between changes to PII such as contact history and discrepancies in account activity.
Spend pattern-based monitoring
If somebody systematically shows cash flow trends within parameters and suddenly anomaly detection determines a shift, it may fraud. These events provide the institution an opportunity to reach out pro-actively to the customer, determine fraud or up-sell opportunity. Does your system confuse variance in behavior as fraud or a chance to communicate positively with the customer? Do you worry about the completeness and timeliness of that customer’s credit history? With the GDS Link BTD solution, you can get beyond short-term blips of data and see location-based trends mapped out over windows of time up to twelve months.
Protecting customers as they seek credit
Indications of fraud are often exposed during loan or credit card application processes. At these times, firms are analysing a person’s credit history to assess if they can handle a loan. With traditional decisioning tools, organisations are left with a limited ability to protect themselves and their customers. Risk analytics systems that provide robust integration with BTD, such as GDS Link, create a more granular and more strategic view of interactions between individuals and their financial services providers. This lets you assess instances of potential fraud and verify the identity of loan applicants with greater precision.
Banks and fintechs are embracing digital transformation in an effort to better keep up with shifting customer demands. Bank transaction data can advance your ability to keep pace with the market and unlock robust capabilities. Want to learn more? Check out our whitepaper, “The Evolution of Bank Transaction Data,” for a detailed look at what the technology entails.
About the Author
Carl Spilker, Vice President of Analytics
Carl is an accomplished executive within Global Consumer Lending, boasting over 20 years of industry experience. Carl has a proven track record in delivering consumer lending products and utilising complex analytical instruments such as AI, Machine Learning and traditional multivariate models.