-
@sktime/core-developers, @XinyuWuu, @fnhirwa, I think we ought to untangle terminology for "global" in the code base and especially in user facing documentation and tutorial notebooks.
Currently, i…
-
Dear authors,
Thank you for this very interesting benchmark contribution.
Currently the splits are [programatically defined](https://github.com/kitamoto-lab/benchmarks/blob/1bdbefd7c570cb1bdbdf9e0…
-
**Describe the bug**
I am trying to create a working example of using ConformalIntervals for time series forecasting. I am using a ML regressor within make_reduction(LGB) to train my model. I run i…
-
Hi, so I trained the interpolator network on the spring mesh database and killed the run after a few epochs. This saved the last.ckpt file locally in the results/checkpoints directory and gave me a ru…
-
Add the cross- and termporal forecasting based on R packages:
[thief](https://github.com/robjhyndman/thief)
[MAPA](https://github.com/trnnick/mapa)
[FoReco](https://github.com/daniGiro/FoReCo)
I a…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Current Behavior
When making bulk timeseries predictions (e.g. the below), I would expect there to be HORIZON …
-
We could really use at least one large question set on what the future of forecasting will look like. Some ideas:
1. How popular will [judgemental forecasting] be in [5,10,20,50] years?
2. How impor…
-
🔍 Problem Description:
The rapid advancement of technology and online platforms has led to a significant increase in the amount of data generated. Predicting sales trends can be a complex challenge f…
-
Hi Gregor, many thanks for an amazing package and all the great work!
Is there a way to use the models we estimate for out-of-sample forecasting (maybe some of the underlying filtering packages sup…
-
Add the ability to extend beyond the last observed data. This requires:
- [ ] Extending `enw_preprocess_data()` to have a horizon argument. This needs to extend the metadata by this number of days…