COVID-19 has upended fraud detection

Enjoy complimentary access to top ideas and insights — selected by our editors.

The rapid move to online commerce during COVID-19 has created a perfect storm for fraud detection. There are more people online, new people online, and money is coming from new places.

All of these factors can make traditional fraud detection more prone to false positives and false negatives, even if the actual rate of real fraud doesn’t change (and there are reports that that is going up, too).

When there is a surge in new data, old data is often not enough to evaluate and authenticate identity accurately. While traditional data sets are still a vital piece of any fraud prevention approach, companies should also look to fill in newly created gaps with more real time, predictive and intent-based options.

Many traditional models are based on behavior patterns that have been completely and perhaps permanently, disrupted by COVID-19. Many methods of fraud detection rely on aggregated data from past behaviors. These methods usually follow two models. Organizations establish their own risk thresholds and structure their analysis around that, or they rely on machine learning to establish a new baseline of individualized normal behaviors.

There are problems with these methods during COVID-19. First, an organization’s risk thresholds must be adaptable as new customers come in and current customers behave differently. And machine learning models are less reliable because the baseline is not as stable as it used to be.

For example, a third of consumers age 65 and older planned to increase spending online because of coronavirus. Bulk purchases and purchases of unusual items that fall outside of a typical buyer profile are more common. People have received government checks, and so spending is coming from new sources. People are also using new technologies to transact such as Venmo, PayPal and Apple Pay.

When people stop behaving the way they usually behave, fraud detection can be impacted significantly. New customers may be flagged as fraudulent, while fraudsters might go undetected due to a surge in unusual activity that obscures their activity.

When there are a lot of new customers and new activities, one source might not be enough to determine if activity is real or fraudulent. Companies should beef up on data that proves that elements like customer behavior, location and spending are accurate. Someone might have an official residence in New York City, but they're spending time in the country during the pandemic. A person may have decided to travel for the first time in several months after having sheltered in place. These are very real behaviors that would look suspicious to fraud detection based on older or more static data.

Companies should find data partners that can help prove or disprove assertions about an individual. There are data partners that offer validation of location by mobile phone, for example, or that share recent online spending habits or home rental information. If someone has looked for houses for rent in a certain area, they may end up purchasing items and sending them to their new rental address.