AI Agents for Bayesian Data Science

of people don't know what the, like, I guess maybe I do think you were talking about it for folks who don't know about the difference between a Bayesian approach versus more

traditional

approach to machine

learning or,

uh, statistical learning.

I know you're, I know you're getting into it, but like a quick, I guess a quick summary of.

how those approaches are different and what they let you do.

Yeah, absolutely.

So the, um, I mean, there's all kinds of ways of, um, comparing Bayesian modeling to other things.

Um, the most instructive I think is machine learning because that is like the, um, the big competitor.

And, um, actually it's not really a competition because I think just like the problem domains or the type of things you want to answer are usually quite different.

But I would argue that you actually want to, that most of the questions in business certainly are actually, uh, causal questions at heart, right? Because what I mentioned with the taking actions, right? So in business, really, do you just want to know like, Oh, like next quarter's, um, sales are forecasted to go up or down, right? So that is good to know, right? So having just like a black box model where I don't really care about like how it made that particular forecast, right? How it came up with that.

So that's why these models are often called black box.

That then is like...

Good to know, but really, I mean, the next question will be, okay, well, how do I stop it from going down, right? And then things like seasonality come in, right? And those are things that really, when you include in the model, and that's the core difference between a Bayesian model where rather than just fitting some relationship, some correlations, you're exploiting some correlations in your data to predict the outcome, here we're applying already what we know, building that causal model, and then with that mechanistic understanding we can simulate the world and then we can manipulate basically this simulator right to like model scenarios where we do take certain actions and then um we we know basically what the uh what our decisions really lead to right and then select the best one so um Yeah, but the cost that you pay is that you have to build that causal model in the first place.

So that's the effortful part, and that's why companies come to work with us because they're like, oh, okay, well, we understand that there is this model that is really powerful once we have it, but the question is, how do you get it? And so we come in and we do that, and it's quite difficult, right? So getting a model that is really...

trusted and verified and has good convergence and all the nice properties of what you want, right? A model that you can trust ultimately, right? That's what it's about.

And that scales.

So that requires a lot of work.

You need to work with stakeholders to really understand it.

And that is extremely valuable work, right? Because in solving the problem, you're also understanding the problem and learning about the problem.

So I think that's a fair cost to pay in a way.

But obviously, if you can avoid it, then you'd want to make it faster and more user-friendly, right? And that has always been the thing that really bothered me with PyMC and Bayesian modeling in general is that it's just like really, really hard to use, right? So the software is like from experts for experts.

And now with AI, these methods can be made accessible to a lot more people, a lot more intuitively.

And that I get incredibly excited about is that like this premise back then of like, oh, well, let's just really revolutionize decision making on a global scale by having like an open source package that provides that right and you can apply in all kinds of different domains to really have that impact if you have expertise well if we lower the expertise we can multiply the impact uh that we're having and just build like really really smart better decision making systems and and that i think the agents will like play a fundamental role in