In the current retail environment, omnichannel shopping is surging in popularity. Whether ship-to-home, curbside pickup or buy online pick up/return in store (BOPIS/BORIS), there is no denying that retailers who embrace and master the art of omnichannel retail will be the most successful in the near and distant future.
With this increased reliance on omnichannel retail comes a need to combat omnichannel fraud. Every year, “lone wolves” and organized retail crime (ORC) rings around the world steal hundreds of millions of dollars by exploiting gaps that exist between brick-and-mortar and e-commerce channels. Additionally, given the pace of change, elements of the customer experience are often rolled out much faster than the associated fraud controls can be put in place. Only with an advanced analytics solution like prescriptive analytics can retail loss prevention (LP) teams successfully uncover and eliminate this fraudulent activity.
Prescriptive analytics is an analytics methodology that combs through data and determines:
- What is happening
- Why it happened
- How much it is costing you
- What to do about it
- Who should do it
Here are three common types of omnichannel fraud that retailers have rooted out with prescriptive analytics.
This method is a particular favorite of ORC rings. In the hyper-competitive marketplace, countless manufacturers strive to design affordable products that are quite similar to their premium, name-brand counterparts. Many ORC rings are now using these knockoffs to commit BORIS fraud. The ring participants will order a huge quantity of premium items from a retailer (typically online, as the maximum order size is much larger than in store), only to return a cheap knockoff instead. The return is most often done in store, where the busy associate is less likely to notice the difference. Thus the fraudsters receive a full refund for the order, and still keep all the premium items to sell for cash.
The key to catching this type of fraud does not require identifying the returned items as knockoffs. Rather, it’s about identifying the conspirators’ buying/returning patterns. If a fraudster successfully pulls off a product switch-out scheme once, you can bet he’ll do it again and again. This will create a highly suspicious behavior within your data—consistent purchasing and returning of high-dollar-value orders. Rather than digging through a paper report for this evidence, prescriptive analytics can be configured to identify it automatically.
One of my customers, a hardlines retailer, experienced this exact problem a year ago. Only after it adopted prescriptive analytics did it identify a longtime ORC ring that was purchasing high-end wall outlets online and returning a similar-looking outlet from a dollar store in person. Although it quickly broke up the ring after making the discovery, the retailer had already lost nearly half a million dollars to this scheme.
Payment Card Fraud
Credit-card thieves often turn to e-commerce for using stolen cards, as there is no cashier to verify the name on the credit card matches the user’s ID. Fraudulent online purchases impact retailers in two ways—both through the stolen merchandise and potential chargebacks from the real card owner once they realize their card is being used illegally. In the past, identifying this activity was fairly straightforward—the retailer’s LP team would look for high-dollar-value orders for which the tender card name did not match the recipient’s name. Today’s e-commerce fraudster is much cleverer, taking advantage of expanded gift-shipping to send items to themselves without raising suspicion.
To avoid the lost merchandise and costly chargebacks associated with fraudulent online orders, your best bet is to look to your data and stop them before they reach their destination. I recommend configuring your prescriptive analytics solution to analyze order destinations. Specifically, one of my fashion customers configured theirs to flag single addresses with multiple high-dollar-value orders en route simultaneously. This behavior means either the order-placer is exceptionally absentminded, or they are using multiple stolen credit cards to place these orders. Recently, my customer used this logic to identify 93 orders destined for a single address in Florida. Thanks to the prescriptive analytics solution’s timely alert, its LP team was able to confirm all the orders were purchased on stolen credit cards and intercept the shipment. Nearly $10,000 worth of merchandise was returned to the warehouse and the retailer avoided any losses from this case.
Packages will get lost in transit at times and never reach the customer. To make up for this, some retailers, especially those in fashion, send the customer not just a replacement product, but also a gift card or discount on their next purchase. This practice is called “appeasing” and carries a major risk of fraud by e-commerce customer-service representatives (CSRs). Retailers have caught CSRs sending these replacement orders to themselves or acquaintances, sometimes as part of a larger ORC ring. Such incidents can cost many thousands of dollars in a very short time, making it critical to identify and stop them as fast as possible.
There are two telltale signs of appeasement fraud—suspicious addresses and suspicious frequency of appeasement. The former approach involves looking at the destinations of appeasement orders. Suspicious addresses include:
- Current/former employees’ addresses
- Addresses to which multiple appeasement orders have shipped
- Addresses that do not match the purchaser’s address on file (the purchaser may be sending the appeasements to an ORC kingpin or collaborator)
- Addresses around call centers or warehouses
- Appeasements headed to any of the above destinations should be scrutinized carefully.
The frequency approach involves using machine learning to calculate the average rate of appeasement across all your CSRs. From there, the right solution, like prescriptive analytics, can easily identify any cashiers appeasing orders at an above-average rate and flag them for follow-up. The frequency approach helped one of my customers uncover an ORC ring falsely appeasing orders and sending them to conspirators across their state. The ring had even infiltrated the company’s temp-hiring process—meaning that more conspirators were being hired every week. Thanks to the insights of its prescriptive analytics solution, the retailer broke up the ring and saved $50,000 a month.
For more information on the use of prescriptive analytics to identify and eliminate fraud, contact the Zebra Analytics team at email@example.com.
About the Author
Scott Pethuyne is a member of the Industry Solutions team at Zebra Analytics. He comes from an accomplished background in asset protection with tenures at Justice, Ascena Retail Group, and Designer Brands (formerly DSW). He uses his intimate knowledge of AP strategies and the Zebra Prescriptive Analytics solution to show retailers how to combat fraud, drive efficiency, and strengthen revenue and margins with Zebra Prescriptive Analytics.