Fighting Organized Retail Crime with Prescriptive Analytics

Fighting Organized Retail Crime with Prescriptive Analytics

In the past couple months I’ve traveled to many loss prevention events and conferences. Amidst all the great conversations around modern loss prevention and asset protection  (LP & AP), every year there seems to be one especially hot topic. This year it was the evolution of organized retail crime (ORC). Everywhere I went in the past couple months – whether a full-scale event or a simple customer meeting – there seemed to be some buzz about ORC’s new cases and how to protect retail assets from it.

I’m not surprised — ORC is something all retailers should be concerned about. Every year ORC  evolve and gets more subtle, more damaging, and more difficult to catch. Retailers need to take action, now.

The best way I know to identify and resolve cases of ORC is investing in a prescriptive analytics solution, like the one we offer at Profitect. Our solution automatically analyzes data for any behaviors that could potentially indicate ORC-type behavior and distributes the detailed findings as an opportunity. It also provides a set of prescriptive actions that is sent directly to the appropriate stakeholder, informing them how to respond to eliminate the ORC and apprehend all involved. Here are a few of our most noteworthy successes against ORC:

Self-checkout fraud

A national grocer adopted our Inventory module to ensure better margins and inventory accuracy. Soon after deployment, the module’s machine learning and AI technology alerted the grocer’s AP team to an inventory anomaly. A specific store’s meat department had begun the week with just 250 pounds of chicken parts on hand; by Wednesday of that same week, records showed it had sold 505, with no new deliveries. Profitect also identified that beef was moving slowly based on the store’s typical ship-to-sales ratio. Additionally, another, nearby store showed similar behaviors. A Profitect prescriptive action directed the stores’ district AP manager to check pricing-sticker accuracy at the stores and interview the meat employees on duty over the past several days.

Under interrogation, several meat workers confessed their longtime involvement with an ORC ring with a local caterer. The caterer would come into the stores several times per week and order very large quantities of expensive beef cuts, like rib roasts or tenderloins. The colluding employees would attach price tags for chicken parts to the beef, allowing the caterer to purchase them at a fraction of their actual price. To avoid suspicion at the register, the caterer would ring up the beef at the self-checkout line. The caterer would later give the meat employees a kickback for their help.

The retailer pressed charges against all involved employees and the caterer, ultimately recovering $90,000 in losses. It also updated its self-checkout procedures to mitigate future risk, adopting new Zebra technology to identify scanned products with biometric data like color, volume, size, etc. to verify accuracy.


A hardlines retailer’s AP team wanted to identify more-subtle cases of employee fraud, and adopted Profitect’s Sales & EBR module to support its initiatives. Shortly after going live, the solution identified a potential indicator of fraud. Profitect’s machine learning and AI technologies had analyzed and compared transactional and HR data, and informed AP of a strong correlation between sales transactions with the highest-value item voided, and low supervisor presence on the sales floor. The module sent the retailer’s AP team a list of these specific occurrences, along with CCTV footage and a prescriptive action advising them to investigate.

The CCTV footage showed numerous employees passing merchandise to their friends and family at the self-checkout registers. Each time, the employee waited for the customer to ring up their entire order, then voided the most expensive item and placed it in the customer’s bag. More than a dozen employees were terminated and prosecuted, recovering more than $50,000 in stolen merchandise.

E-commerce fraud

A fashion retailer adopted Profitect’s Sales & EBR module as part of an initiative against shrink and fraud. After much success with in-store data, the retailer chose to upload its e-commerce data into the module as well. Within five minutes of deployment, the solution’s machine learning and AI capabilities identified and alerted Asset Protection to some suspicious behavior within the retailer’s call center.

As a customer-service gesture, the retailer allowed its customer service representatives (CSRs) to “appease” products (i.e. offer them for free to dissatisfied customers, along with a $20 gift card). Profitect identified several CSRs who were appeasing many, many more e-commerce orders than benchmark levels. Profitect further identified that the suspect CSRs were shipping the appeased orders to the same five addresses — all of which were linked to their friends and family. The prescriptive action to AP was to investigate the suspect CSRs for potential organized retail crime (ORC) activity.

The prescriptive action led AP to the root cause. These employees had formed an ORC group. Working together, they’d legitimately buy a product online and, after receiving it, would call the center to complain they never got the product. Thus they ended up with a $20 gift card and two products that they could sell or return for cash. With this information, the retailer terminated all involved, saving an average of $50,000 a month.

These are just three of the many wins our retail and CPG customers have realized with Profitect’s prescriptive analytics solution. For more information on prescriptive analytics as a tool against ORC, visit