A couple of years ago, a shoplifter stole products in a D&B Supply store in Caldwell, Idaho. Then a couple of days later, he robbed the series’s store in Meridian, Idaho, some 20 miles away. The merchant’s vice president of operations notified some of the other large retailers in the area, sharing surveillance images of the burglar and details of each offense.
The regional Fred Meyer grocery store was hit next. It shared what it learned, and before long, a community of merchants managed to provide police with a detailed picture of the crook, by way of instance, make of the vehicle and a license plate number. An arrest followed.
In cases like this, a few stores shared information about a criminal and, by so doing, helped to secure their neighborhood community. Imagine if ecommerce merchants could also share customer actions and, thereby, reduce the likelihood of ecommerce fraud?
Alright, see our products:
“One of the things I have realized working in this domain for so many years… is the advantages and disadvantages of artificial intelligence and machine learning and, also, the dependence on getting good data tools,” said Uri Arad, vice president of product and research and co-founder of Identiq, which delivers a peer reviewed trust system for retailers and other consumer-facing businesses.
That so much of ecommerce fraud prevention is dependent upon data and patterns of information”is especially important when you have to manage risk from an unknown,” Arad said. “An unknown might be an individual that you haven’t seen before, a credit card that you have not noticed before, or a considerable change in behavior. So all those things introduce new patterns and new data.”
“Combined with the increasing sophistication on the surface of the bad guys… telling good from bad is becoming a more challenging problem to resolve,” Arad continued.
For card-not-present transactions, telling a fantastic customer from a bad one is becoming harder. Photo: Bermix Studio.
Solving this problem is vital since trusted transactions are a linchpin of ecommerce retailing.
The client needs to trust that the merchant has properly described and introduced with the solution and the company is going to send that merchandise as promised.
The merchant needs to trust that the customer is a true buyer presenting his own payment card information as opposed to planning fraud.
Many merchants use fraud prevention tools to sort out secure and dependable transactions from ones that are questionable.
When a mid-sized or company ecommerce provider encounters a new client, a customer whose information has changed, or a shopper exhibiting new behaviors, that merchant will often introduce friction into the transaction.
This friction may take one or many forms. A few of those steps will be invisible to customers. Others will influence the purchasing experience or even kill the transaction.
By means of example, a great deal of automatic fraud-prevention tools will answer the types of unknowns Arad explained in one of three ways.
- Reduce the transaction.
- Hold the transaction.
- Flag the transaction.
In the latter cases — hold or flag — someone in the merchant will take manual action, like reviewing the order calling the client to verify.
But the first case — diminishing the transaction — may be the most damaging when it is incorrect, because the merchant would be turning into a real, trustworthy customer. It’s called a”false positive.”
“False positives are a result of the inability to accurately measure the amount of fraud risk in a transaction. The true consequences of false positives could be difficult to measure, but lost earnings are a direct impact,” wrote the authors of an ebook,”The Silent Sales Killer: False Positives,” from Kount, a leading fraud-prevention provider.
“Too often, false positives go unnoticed as online businesses perceive them as successfully thwarted fraud as opposed to foregone sales. Yet false positives harm online businesses financially in four fundamental ways,” the ebook continued.
- “Immediate earnings reduction. Every order wrongly turned down is earnings not accomplished.”
- “Lost customer lifetime value. Lifetime customer value is the complete profit expected from all future purchases by a customer. Legitimate customers which are wrongly rejected will often stop buying from that merchant permanently.”
- “Wasted acquisition spend.” All your company’s marketing and advertising is wasted on a false positive.
- “Degraded brand image. In today’s connected world of social media and viral posts, 1 shopper’s experience with a false positive can suddenly reach thousands of customers and potential customers. While difficult to quantify, the effects of negative publicity is nonetheless real.”
Fraud prevention companies take various approaches to manage actual card-not-present fraud and protect against revenue-damaging false positives.
Many use artificial intelligence, which may be applications using algorithms and pattern recognition to accomplish a task that would usually require individuals. But Identiq is notable because of its peer reviewed approach.
After an Identiq member, a company with millions of customers, experiences a new buyer, it can ask other members around the community in their expertise with the shopper, if any. This is done anonymously so that every person’s privacy is protected in accordance with the General Data Protection Legislation in the European Union and the California Consumer Privacy Act.
The point is that while a brand new client may be unknown to a specific merchant, another merchant or a favorite paid app has probably experienced that identical shopper.
Pretty much every fraud prevention software provider and financial institution is trying to boost ecommerce fraud detection while avoiding false positives. As Arad stated, in the long term, it is dependent upon the data. Thus sharing customer experiences could help all participating merchants.
►►► ConnectPOS is a cloud-based POS software compatible with multiple platforms including Magento, Shopify & Shopify Plus, and BigCommerce.
Our Feature Posts: