https://github.com/nixtla logo
m

marah othman

05/05/2023, 9:34 AM
hi all, i need your opinions about cross validation in general do we get a good benefit from that in time series, any advice we be helpful for me?
k

Kevin Kho

05/05/2023, 9:40 PM
1. You know that cross validation for timeseries is slightly different right? Like this 2. Yes it benefits as much as normal machine learning. It gives you a clue how robust the model is to different folds
m

marah othman

05/08/2023, 9:27 PM
you mean by slightliy is the sampling for data flod shloud be next to each other right?
k

Kevin Kho

05/08/2023, 9:28 PM
Yeah and test set in the future