dssg / dssg/randomize_your_data
potential new ways to introduce leakage
Open
- Dominant language
- Jupyter Notebook
- Stars
- 8
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
1. indicator variable for regime change. standard cv would use it for almost every fold. temporal wouldn't until the regime change hit.
2. continue to use DGP with ~5 Xs, but then do variable selection on the entire dataset using 1,000 other randomly generated variables. Only keep the k most predictive.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.