Nixtla: Deep Learning for Time Series Forecasting

[@virgilioespina]

Thank you for this presentation. I am now comfortable reading the paper.

[@bhupendrakumar1753]

I love your package - neuralforecast. It has outperformed other algorithms in my case.

[@gstankevix]

"Facebooks prophet might be many things but it's definitely not a model for forecasting time series at scale", well said.

[@snipers1692]

It takes alot of time for forcasting

[@thuggfrogg]

Amazing! Thank you for your work and sharing it :) .

[@fabianaltendorfer11]

Very nice presentation!

[@jinluwang5671]

What about distributor forecast? Would inventory info (out of stock, in stock), customer sales be extra features for any model?

[@jeremykusnadi5148]

how can we do a hierarchicalforecast with an exogeneous variable? Is it possible yet?

[@aronabencherifdiatta149]

Thank you very much for this amazing video. However, how do we get hold of the presentations ? 👏

[@phaZZi6461]

notes for myself:
11:44 - beamsearch?

[@tisisonlytemporary]

Good stuff!

[@ShaneZarechian]

The zillow mention haha

[@LindaMartin-p1t]

Hermiston Spring

[@LeightonSteward-q9x]

Larson Mountains

[@BasilEkholm-j3m]

Cayla Island

[@mehdialibegli8233]

ok

[@BettyMcNeil-h2j]

Kiehn Passage

[@khalidfarooqkf1756]

Kaggle

[@EvanShlom]

doesnt even work with exog variables. fat load of horse shit unless this is fixed or someone can point me to an example of someone having success with this using exogenous variables. massive waste of time