[srean]

Except that their success in the time series domain has been rather lackluster and elusive. It will s one of the few domains where old school models are not only less work to maintain but also more accurate. There are a few exceptions here and there. Every year there are a few neural nets based challengers. You can follow the M series of computations from its start to see this evolution.

[robot-wrangler]

Maybe because useful time-series modeling is usually really about causal modeling? My understanding is that mediated causality in particular is still very difficult, where adding extra hops in the middle takes CoT performance from like 90% to 10%.

[srean]

Yes causal models are hard.

NNs do ok on those time series problems where it is really about learning a function directly off time. This is nonlinear regression where time is just another input variable.

Cases where one has to adjust for temporaly correlated errors, those seem to be harder for NNs. BTW I am talking about accuracies beyond what a typical RNN variants will achieve, which is pretty respectable. It's the case that more complicated DNNs don't seem to do much better inspite of their significant model complexity.

[orangemaen]

LightGBM won M5 and it wasn't even a competition.

[srean]

The task was slightly different and favored GBMs. Note they aren't NNs whose underwhelming performance was what my comment was about.

The M series of competitions change the tasks every year to explore what models perform best under different scenarios. As I mentioned, neural network based models win here and there, but very spotty performance over all.