I suspect that adding such complexity to the QB rating system would have less of an effect than you might think. There seems to be something of a diminishing return on adding parameters to such analytics. You sometimes get weird results that end up muddying the water rather than clearing it up and sometimes you can add all kinds of granularity to a computation and end up with a nearly identical result that makes all the detail gathering a waste of time and energy. There's no way to know though, until you try it!
I haven't heard anything yet, but I'm not paying close attention either so. It'd be surprising if some known but not well-known QB out of the past winds up being christened the Greatest Of All Time. It might be able to however, tell us just how good someone like Aaron Rodgers truly was during his long prime era, when he basically ran away with the QB ratings all the time, he was really accurate and talented, we all know, but he might have been even better than we all think too, is my thinking. He almost never had elite receivers, like Tom Brady and Joe Montana at times enjoyed in their dominant careers, for example. If Rodgers ever got a Randy Moss or a Jerry Rice, he might have run away with the GOAT title.
I'd be shocked to find out that there isn't anyone already trying to figure out ways to use AI in a manner close to what you're suggesting. I'm certain that it has everything to do with the new propensity of teams to go for it on fourth down now. That didn't hardly ever happen before. Now it's multiple times a game. AI has got to have something to do with that change.
I'm not sure about this (nor about the contemporary novelty in the NBA to focus on taking threes so much that it at times seems ridiculous). This has the signature of MLB's "Money Ball" phenomenon, aka "Sabermetrics". They didn't need AI to come up with this, is my thought.
www.muellershewrote.com
