Why General AI Models Fail at Financial Fraud | Suddu Seshadri

Mm.

You said fraud is moving really fast with AI.

Yeah.

What's happening right now?

Yeah.

So with AI, as you can see, uh, across whether it's identity, synthetic, or first-party fraud, all of these are, uh, independent use cases across fraud.

And, uh, with AI, it's become easier for you to be able to replicate all of these scenarios across the board.

But at the same time, when you look at, uh, how Plaid is connected across ni- nine thousand applications and twelve thousand financial institutions with millions of users, especially about one to two American citizens are now on Plaid, the good actors have to connect via Plaid as well as the bad actors have to go through the same network and connection.

So what we have been able to do is use the depth of that particular graph to sequence it and model it in such a way-

Mm

... that we can identify anomalies and detect those anomalies to be able to id- identify fraud and, and prevent them before a transaction goes through itself.

So fraud is really moving fast, and, uh, as you can sequence events and activities to be able to understand where there is these anomalies happening, you can actually catch fraud faster too.

So it's a continuous cat and mouse game which you're playing, and I think it's only getting faster and faster as we think about it.

Mm.

You said fraud is moving really fast with AI.

Yeah.

What's happening right now?

Yeah.

So with AI, as you can see, uh, across whether it's identity, synthetic, or first-party fraud, all of these are, uh, independent use cases across fraud.

And, uh, with AI, it's become easier for you to be able to replicate all of these scenarios across the board.

But at the same time, when you look at, uh, how Plaid is connected across ni- nine thousand applications and twelve thousand financial institutions with millions of users, especially about one to two American citizens are now on Plaid, the good actors have to connect via Plaid as well as the bad actors have to go through the same network and connection.

So what we have been able to do is use the depth of that particular graph to sequence it and model it in such a way-

Mm

... that we can identify anomalies and detect those anomalies to be able to id- identify fraud and, and prevent them before a transaction goes through itself.

So fraud is really moving fast, and, uh, as you can sequence events and activities to be able to understand where there is these anomalies happening, you can actually catch fraud faster too.

So it's a continuous cat and mouse game which you're playing, and I think it's only getting faster and faster as we think about it.