[ML] Improve robustness w.r.t. outliers of detection and initialisation of seasonal components #90
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
tveasey
force-pushed
the
enhancement/improve-periodicity-test-robustness
branch
from
74935cf to
005641a
Compare
…isation. Some test fixes
tveasey
force-pushed
the
enhancement/improve-periodicity-test-robustness
branch
from
005641a to
0792d04
Compare
edsavage
approved these changes
May 8, 2018
tveasey
force-pushed
the
enhancement/improve-periodicity-test-robustness
branch
from
a42c55b to
db51441
Compare
|
Please additionally do when backporting this to 6.x |
tveasey
added a commit
that referenced
this pull request
May 22, 2018
…on of seasonal components (#90) This makes two principle changes: 1) iteratively reweights outliers w.r.t. the seasonal component under test and for initialisation. These are defined as a fraction of values with highest residual w.r.t. the component's predictions. 2) switches marginal test decisions for decomposition components to use logistic regression on top of the various factors, i.e. variance reduction, autocorrelation, number of periods of data observed, etc.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This makes two principle changes:
I've tested this on a variety of synthetic and real examples where initial periodic patterns are distorted by outliers and this approach has proved effective, see #87 for more details. Otherwise, it seems to have no detrimental effects.
This will affect results on count and metric analyses when there is seasonality and significant distortion due to outliers.