When evaluating AI/ML offerings, how do you decide which is best for you and your organization?
Something that we use to our advantage a lot of the time is… we find the data that we know is good, or the traffic that we know is normal, and we put it aside. And then we focus on what's left. We look at that and we try to figure out what is good and what's not. And we throw that out and we focus on what's left. Eventually we work ourselves down to a data set that's manageable, and then we can figure out what's really going on by looking at the big picture and saying, okay, forget all the noise, right. The noise is good. We've checked it. Let's figure out what we don't know. And that's where we find most of our issues. That's hard to do, but that's really how we do it with bigger data sets. You can't look at it all. You got to start saying, this is good. This is good. This is good…. Oh, what's this? And then work your way from there.