With Bayesian stats, you build a very nuanced model to capture what you know in your head. So random force in neural nets, there's very little you can do besides just tuning some hyper parameters. But with Bayesian models, you can say I'm a news vendor and I have demand for New York and demand for Boston. And I know which day of the week it is. On event days, we might sell more newspapers. That helps you get a more precise estimate.