Edwin Ng

@knkski are you saying you get same result across threads even with the setting `seed=None` ?

So you want to see same behavior on each thread you call `model.predict`? If so, the other around as you described should work by using seed=a_fixed_number. Please let me know...

Can you provide some data / object snapshot when the issue happen? @ggerogiokas

@Garrus990 In orbit, it is using percentile scale like the [np.percentile](https://numpy.org/doc/stable/reference/generated/numpy.percentile.html#numpy.percentile). So in you case, you should specify `prediction_percentiles = [2.5, 97.5]` instead.

I have a couple of comments about orbit: 1. the pypi link from the [leaderboard](https://microprediction.github.io/timeseries-elo-ratings/html_leaderboards/univariate-k_003.html) should be [orbit-ml](https://pypi.org/project/orbit-ml/) 2. most of the models assume users will take care the scaling...

Sorry for the delayed response. After a long break...I'm checking the `orbit_wrapper` [here](https://github.com/microprediction/timemachines/blob/8bceee35601c0a2e9ab18401ae4b71bf512e343d/timemachines/skaters/orbt/orbitwrappers.py#L8) now but I would also like to test it end-to-end. So i'm still looking for some standard...

just curious - why do we have lgt_12 and lgt_24 together in the same [dashboard](https://microprediction.github.io/timeseries-elo-ratings/html_leaderboards/univariate-k_001.html)? I suppose they are working on different series: monthly series vs. daily series (just my...

> Or if you like I can hack [this elo script](https://github.com/microprediction/timeseries-elo-ratings/blob/main/update_skater_elo_ratings.py) so that it runs orbit skaters every time. Maybe let me try studying a bit on the notebooks [here](https://github.com/microprediction/timeseries-notebooks/blob/main/pycaret_microprediction_timemachines.ipynb)...

I've finished the notebooks part for a simple lgt. But that just works for strictly positive values series. I'm also trying to create a `DLT` model. However, I got stuck...

@hiwaveSupport is this still valid?