Building a comprehensive file of each customer is critical for telling good customers from those trying to defraud you.

Thirty good customers are treated like fraudsters, in the hopes of catching one true fraudster. This is because today’s fraudsters are more sophisticated than ever and stopping them has never been more difficult. They have more access to data and finding more creative ways to attack retailers both online and off.  

So companies increase security measures and accept a certain amount of customer disruption as a necessary part of reducing fraud losses. The more notable result: irritated consumers. Today’s consumers have clear expectations. They expect to engage with a retailer easily, be recognized without scrutiny, and make their transactions safely.  The push to stop the bad guys has created friction in this experience. But it doesn’t have to be that way. We recently published a report, Global Business Trends: Protecting growth ambitions against rising fraud threats, providing insight to help achieve a healthy balance between the customer experience and protection.  

A universal view of the consumer is the core of modern fraud mitigation

A multi-layered approach to authentication is considered the gold standard for identifying legitimate customers, but challenging the customer with too many questions often leads to an adverse reaction. Having access and insight into universal consumer behavior down to the transaction level is necessary for fraud mitigation in the future and builds the framework to create a pleasant experience for your consumer.

The importance of profiling a customer goes deeper than just transactions and purchase patterns. You should be looking at their overall patterns of interaction, including: which device(s) do they normally use to interact, have they removed items from their shopping cart, are they comparison shopping, how much time did they spend on a site, number of visits, is the same device representing multiple shoppers (different addresses, credit cards, email addresses, etc.), are they exhibiting rogue behavior, accessing the site through proxies, etc.

advertisement

These patterns help merchants recognize trustworthy from non-trustworthy activities, and build the customer’s profile—which is critical for determining the overall level of risk or trust that the merchant should have with that customer.

Expand your customer view through a blended ecosystem

However, truly knowing the individual customer requires knowledge of a person’s offline and online behavior, not only with your business, but also other businesses with which that customer has a relationship. This is where the blended ecosystem becomes a necessary part of your customer profiling.Many organizations have launched projects to achieve a single customer view: collaborating across internal silos to bring together information about their customers and their interactions.

However, a company’s single-customer view may still achieve only a partial view of the consumer. This is because their view is solely based on their relationship with a consumer, rather than the consumer’s relationship with other companies. Today’s fraudsters have access to a much broader view and they are using it to their advantage. You need to have a similar view of your customers. Participating in a blended ecosystem by working with vendors, customers, partners and even competitors that can bridge disparate data and internal silos, will provide an enhanced customer experience that supports business growth, without sacrificing protection.

Apply right-sized fraud solutions that reduce unnecessary customer disruption

advertisement

The rise in mobile and web traffic is increasing the volume of online purchases and, with the introduction of EMV, more fraud is being pushed there. [EMV refers to chip cards whose improved security at physical stores may drive criminals to target online retailers.] It’s also making it more difficult to recognize your true customer. The rate of disrupted legitimate traffic to actual fraud attempts is at a staggering high of 30 to 1. That is challenging way too many legitimate customers to catch one fraudster.

To reduce customer disruption, while still appropriately managing fraud risks, you need to apply fraud mitigation strategies that reflect the value and level of confidence needed for each transaction. At Experian, we call this right-sizing the fraud solution. For example, if fraud attacks represent 1 to 2 percent of transactions, right-sized solutions should identify no more than 4 to 6 percent of transactions as probable fraud, however if your fraud attacks represent only 0.25 to 0.5% of your transactions, then right-sized solutions should identify no more than 1-2% of transactions as probable fraud. Having the right level of insight into your customers will help you recognize your real customers and further reduce the level of challenges.

Machine learning is a powerful predictor of fraud, but not a panacea

Machine learning has become an invaluable advanced tool in the fight against fraud, and is an emerging trend featured in our report. While this is a great technology, a solid machine learning-based solution also requires specialized expertise to apply rigorous methodology in data analysis and to develop the fraud models to avoid false positives stemming from a model “over-fit” issue. The systems begin to over-process every transaction that comes through, creating hundreds, even thousands, of rules that need to be managed. Instead, a hybrid approach where tempered risk thinking can be applied to all of that great artificial intelligence. Balancing machine learning techniques with using characteristic-based analytics can help to reduce false positives and unhappy customers.

Fighting fraud is like driving down the freeway—you should always be thinking ahead. You already do this when it comes to revenue growth and attracting new customers. Fraud detection and prevention are no different. Companies need to be as forward-looking in fighting fraud as they are in growing revenue and attracting new customers.

advertisement

In order to have the ability to fight today’s fraudsters, which are armed with greater knowledge, resources and agility, it will be crucial for you to have an expanded view of your customer. To accomplish this, it is essential to have collaboration between the product development, marketing, fraud teams and third parties—a collaboration driven by the shared goal of growing a sustainable business and protecting your ambitions against rising fraud threats.  

Experian collects data on consumers and businesses, providing credit reports as well as fraud-prevention and marketing services.

Favorite