Is It Better to Summatively Sum Up Your Time Series Than Summarize Your Models?

If your model throws out a million hot dogs and then you start placing an order an automated order for a million hotdogs actually million might make sense let's say a trillion hot dogs that's gonna be a problem. Ben hinted at a really interesting point in that individual time series is tend to be a lot more volatile but not just that the prediction intervals around those time series is if you sum them up you almost always have an unusable forecast.