[
https://issues.apache.org/jira/browse/SPARK-22081?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ruslan Dautkhanov updated SPARK-22081:
--------------------------------------
Description:
Our SAS gurus are saying they would love to have "Generalized Reduced Error
Logistic Regression" before they would consider moving over to Spark ML.
http://www.riceanalytics.com/db3/00232/riceanalytics.com/_download/ricejsm2008proceedingspaper.pdf
We have a lot of production modeling built on this methodology.
!RELR.GIF!
was:
Our SAS gurus are saying they would love to have "Generalized Reduced Error
Logistic Regression" before they would consider moving over to Spark ML.
http://www.riceanalytics.com/db3/00232/riceanalytics.com/_download/ricejsm2008proceedingspaper.pdf
We have a lot of production modeling built on this methodology.
> Generalized Reduced Error Logistic Regression
> ---------------------------------------------
>
> Key: SPARK-22081
> URL: https://issues.apache.org/jira/browse/SPARK-22081
> Project: Spark
> Issue Type: New Feature
> Components: ML, MLlib
> Affects Versions: 2.2.0, 2.3.0
> Reporter: Ruslan Dautkhanov
> Labels: machine_learning, ml, mllib
> Attachments: RELR.GIF
>
>
> Our SAS gurus are saying they would love to have "Generalized Reduced Error
> Logistic Regression" before they would consider moving over to Spark ML.
> http://www.riceanalytics.com/db3/00232/riceanalytics.com/_download/ricejsm2008proceedingspaper.pdf
> We have a lot of production modeling built on this methodology.
> !RELR.GIF!
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
