Probabilistic Forecasting is something very cool, but it is not approachable in the current state of affairs.Â
While researching probabilistic forecasting in a client project I managed to find a paper which opens the door to any neural network with dropout - which is the majority. That is, we can do probabilistic forecasting with essentially any network!
Intro
This is a blog based on a presentation I did at Foo Café, where we shared a lot of our hard-earned wisdom at AFRY X, mainly based on working with timeseries.
Thereâs both simple and more advanced, hopefully in an easy to understand fashion!
In this post/Jupyter Notebook we'll forecast Cryptocurrency prices using Deep Learning (PyTorch, TF/Keras & darts) and we'll use both both simpler networks and more complex ones like NBEATs.
In this post/Jupyter Notebook we'll look at stocks, forecasting and predictions using classical machine learning (sklearn) approaches.
In this post/Jupyter Notebook we'll look at Time Series and theory surrounding them.