Holland has always been a great point for startups to try out new things, while at the same time you're being forced to look international.

We just had to acknowledge we were not getting up to the speed of frauds as evolving and money laundering as evolving.

The tendency then is of every human being, so I see the fraud, I'm going to stop the fraud, because I don't want that fraud to happen tomorrow again.

But we're getting smarter faster, and so that was a big turning point, so okay, we need to change that approach, and you need a number of frauds before you figure it out what you're doing.

But fraud is only 0.1% of your actual transactions, so that means you throw away 99.9% of your data, and old school game 3, he says, frauds are going to change their behavior, they're going to try to circumvent your rules, they're going to adopt their behavior, while normal customers won't.

So how do I switch it around? How would I have found this type of fraud while not looking at the actual fraud itself?

In some ways, my whole career was shaped by a decision someone in HR made before it even started.

I was part of a graduate recruitment intake, one of a dozen like-minded kids chosen to help build out an experiment capital one was running in South Africa.

Now we really could have been shuffled up and spread out in any order, but apparently at the very last minute, my assignment was switched.

So instead of joining the scorecard building team in the mass market loans division, that went to my water polo playing male modeling on the side colleague,

and the credit card fraud team got me, Q some lighter to disappointment from some of my teammates, and for me, a career that was close enough to scorecard builders that I could eavesdrop on their chat, but not so close that I could do their job for them.

So some of you know better, but I'd always simplify the concept of modeling by saying that the target variable should be the thing that is uncommon.

Most people will repay their loan, so we model defaults. Most people in collections don't pay, so we model propensity to pay. Most transactions are legitimate, so we model for fraud.

But if you think about it for a minute, frauds are intentionally elusive. They actively change their patterns of behavior when they always stop working.

Real customers don't do that. So we're aiming for removing targets, when a still one is right there.

Short slot, today's guest thought about it and flipped the transaction monitoring model on its head. Welcome to how to lend money to strangers with Brendan LeGrange.

Short slot, co-founder of Signal. Welcome to the show. Thanks, great for being here.

Signal provides automated machine learning software for transaction monitoring, so a fairly technical niche. What did your early career look like and how did it set the groundwork for what you're doing today?

Well, I've never had any linear line in my life. Even going back to school, I was great in math, horrible in languages, dropped out, came back in again. Same thing with university decided, I want to change the world to digital math and went to sociology and anthropology.

I figured out I wasn't really good at that. So I finished it at some point in the time, but did a lot of other stuff travel the world was active in student organizations called Isaac, which a lot of times still builds my international connections.

Then decided to still want to change the world went to the United Nations, wrote economic reports about the role of youth or the lack of the role of youth.

Nobody was reading those reports or they were reading with nobody's acting on it. What am I going to do with my life came back to Holland.

...