The first big neural networks deep learning moles was actually in a bank about risk tolerance and risk app type.  This lends itself well to the use of NLP and AI in Retail Banking going forward.

It was really based on strictly AI, not really looking at an NLP and those kind of signals, largely looking at who’s going to default on certain bones. 

Large banks have been doing this for  five years ago, so for half a decade, they’ve been looking to assess risk, especially in the retail world as much as possible. 

In the commercial banking side and the investment banking side, they have a lot more money and a lot more budget, so they’re even further ahead in terms of the AI used and the techniques they use, however, in retail banking it largely is about risk tolerance and that’s a very nice way to look at fraud.

There may be opportunities for money laundering, cause you’re talking about loans or disposition of assets and you have to report all those sort of transactions as well, just like in the world of insurance so much of this is. 

At the end of the day applied for as you’re putting your information into these applications, it’s very possible and plausible that these banks actually do a sort of NLU understanding of the application to try and look for signals that may point them to fraud, so that’s the application of the retail side, now the other portions are more of the internal operations of a bank because there’s often you have a lot of actors in a bank there’s thousands of people in large bank organizations and it just takes one person to be kind of naughty to cause the whole bank, a whole bunch of backlash.