[Blog] Reducing AD False Positives Through Algorithmic Improvements #3524
Conversation
…es Through Algorithmic Improvements This PR contains the content for publishing the blog on Reducing AD False Positives Through Algorithmic Improvements. Signed-off-by: Kaituo Li <[email protected]>
kaituo
requested review from
elfisher,
AMoo-Miki,
nknize,
krisfreedain,
peterzhuamazon,
CEHENKLE,
dtaivpp,
kolchfa-aws,
nateynateynate and
natebower
as code owners
Signed-off-by: Fanit Kolchina <[email protected]>
|
@kaituo Doc review complete: could you please review my changes and verify that they preserve technical accuracy? I changed some of the terms (like "alert once suppression" -> "grouped alerting") for more intrinsic understanding. Also, could you please change the headings in the images so they match the new headings? And please use sentence case for headings (first word capitalized and the others lowercase, unless it's a proper noun). Thanks! |
|
@kaituo - Have you incorporated Fanit's suggested edits into the PR? |
Signed-off-by: Kaituo Li <[email protected]>
|
@pajuric Just incorporated @kolchfa-aws and Nina Mishra's feedback. @kolchfa-aws Please take a look. |
Signed-off-by: Fanit Kolchina <[email protected]>
Signed-off-by: Fanit Kolchina <[email protected]>
|
@kolchfa-aws The doc review looks good. |
There was a problem hiding this comment.
@kolchfa-aws Editorial review complete. Please see my comments and changes and let me know if you have any questions. Thanks!
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
|
|
||
| {:class="img-centered"} | ||
| When excluding the first 20% of data as a probation period, precision improves across datasets. This adjustment highlights how RCF becomes more accurate after observing enough historical data. The results of the last 80% of the dataset are summarized in the following table. | ||
|
|
There was a problem hiding this comment.
Line 203, first sentence: "of the data" => "of the dataset" (to match the last sentence)?
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
Co-authored-by: Nathan Bower <[email protected]> Signed-off-by: kolchfa-aws <[email protected]>
|
@pajuric Please update the meta/keywords for this blog, and it'll be ready to publish. |
| - technical-posts | ||
| has_math: true | ||
| has_science_table: true | ||
| meta_keywords: anomaly detection, false positives, algorithmic improvements, OpenSearch, nab benchmark |
There was a problem hiding this comment.
Please update the meta with the following:
meta_keywords: anomaly detection, OpenSearch RCF algorithm, Random Cut Forest, value vectors, Numenta Anomaly Benchmark, algorithmic improvements in OpenSearch
meta_description: Explore how OpenSearch 2.17 enhanced the Random Cut Forest algorithm, making is possible to reduce false positives by 94.3% while maintaining detection accuracy. Get benchmark results and read practical studies.
| authors: | ||
| - kaituo | ||
| - kolchfa | ||
| date: 2024-12-26 |
There was a problem hiding this comment.
Please update the publish date to today: 2025-02-05
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
_posts/2024-12-26-Reducing-false-positives-through-algorithmic-improvements.md
Outdated
Show resolved
Hide resolved
Signed-off-by: kolchfa-aws <[email protected]>
|
@nateynateynate @krisfreedain - Please help push this live. |
|
@peterzhuamazon - Would you be available to help us push this live? |
|
I will update the time from 2024-02-05 to 2025-02-05 soon before production. |
Description
This PR contains the content for publishing the blog on Reducing AD False Positives Through Algorithmic Improvements.
Issues Resolved
#3523
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the BSD-3-Clause License.