Who is the Saturday Fraud Strategist, with Hailey Windham

So let's start with the Frogster and the machine learning algorithm.

I mean, I'll say that skepticism, I think it's ingrained in me in general.

Maybe that's, you know, like me always thinking like an analyst and always kind of like thinking critically about problems, solutions and so on.

But I think that as a fraud fighter specifically, I have this, you know, as I said, a very ingrained notion that if something looks too good to be true, it's too good to be true.

And because this is how fraud works and this is how you get scammed.

But because, you know, how many times did I write a rule and, you know, was super proud about myself just to find out, you know, it's like, yeah, I blocked like 100,000 accounts, but none of them ever kind of like, you know, transacted or they did transact, but some other rules already blocked them or whatever, you know, how many models did I, you know, launched and, you know, saw completely different results in production as opposed to what we've seen in the simulation.

So it happened to me so many times in the past that, you know, I'm kind of like, it feels to me that I'm trained to immediately start looking at the bugs and the overfitting and the issues when I see very good results.

And the case that you referred, I actually wrote about it long, long, long time ago, like almost two years ago.

Like my most costly mistake was when we launched a new algorithm at Frogster.

And, you know, there was some like research project and the data scientists came back with very good results, much better than our like super sophisticated algorithm, proprietary technology, blah, blah, blah, that we had back there, back then.

And the algorithm that he trained was, let's say, very simplistic in terms of like the architecture and technology.

And I couldn't believe that's the case.

So I sent the team to do more experiments and more experiments and more experiments, like one after another.

And always, okay, let's test it on this vertical and let's test it on this fraud trend.

And it never ceased.

And in the end, I found out that, yeah, it's just a better model.

And we went out and shipped it to production.

But it took a year since the research was done and until it was...

in production, mainly because I didn't accept that these results that look to me to be true, that they are correct.

You know, we talked about it before.

I mean, like we just had it, we literally just published the foundation model that we trained at Sardin for issue and fraud.

And I remember that, I don't remember who put me on that.

I think it was, maybe it was Supes.

Yeah, we've done some research.

Let's write about it.