How retail is using AI to prevent fraud

Jennifer: He says fraud management in places like this has changed quite a bit since he started this job. For example, they set up filters based on some simple questions.

David Cost: Was it a customer we’d seen before, right? We had certain flags that we would look for and someone would manually review those orders and kind of guess whether they thought that order was good or not. We ship it and if it turns out to be wrong, we, the retailer, you know, take that loss. So it’s like someone stole those goods. It’s the same as shoplifting. You know, and it can, it can have a real impact on your business and you want to be careful. If you’re too careful, you’ll turn down good business. I mean, there’s nothing worse than taking a customer with a good valid form of payment and telling them, no. Sorry. Doesn’t look quite right, so we’re not going to ship it.

Jennifer: One place Rainbow ran into… was doing business with buyers in other countries.

David Cost: So they place the order from one of the islands in the Caribbean. So their billing address is a Caribbean address, they mainly ship the goods to a reshipping address in Florida or Texas where a lot of orders are combined to get to the island, right? And then they are taken to those islands. These are good customers, but for traditional fraud, seeing that foreign credit card, foreign address, but an American delivery address would set all kinds of alarm bells ringing. So the refinement of the AI ​​to help us now accurately figure out what is a good order and what is a bad order allows us to increase our level of customer service … So that we take care of customers at the same time, minimizing the potential loss to the business, with those orders that we would fulfill and ship and then not get paid.

Jennifer: Rainbow uses a tool from the fraud detection company Signifyd… and he says they are rejecting less than 1% of their orders these days.

David Cost: Back in the day, when we had to do all this manually, they would go to Google Maps and look up the address to see if the address looked legit. You know, now with the sophistication of technology to know who you are, where else have we seen you order, digital IDs on your device, distance between your billing and shipping addresses. So many factors. So again, even five or six years ago that process was manual and it might take a day or two, you know, now they’re made in fractions of a second.

Will Douglas Heaven: I mean, this happened to me yesterday, actually, you know, I got a text. I had taken my car to the garage and, you know, put a bigger amount on it than usual.

Jennifer: That’s Will Douglas Heaven, Tech Review’s senior AI editor.