Maniphest T121350

Deploy tuned random forest model for wikidatawiki
Closed, ResolvedPublic
Actions

Assigned To

Authored By

	Halfak
	Dec 13 2015, 4:50 PM

Tags

Referenced Files

None

Subscribers

Description

Tuning reports suggest that we can get a very high amount of fitness out of an RF model. See https://github.com/wiki-ai/wb-vandalism/blob/master/tuning_reports/wikidata.reverted.roc_auc.md

Event Timeline

Halfak created this task.Dec 13 2015, 4:50 PM

Halfak claimed this task.

Halfak raised the priority of this task from to Needs Triage.

Halfak updated the task description. (Show Details)

Halfak added a project: Machine-Learning-Team (Active Tasks).

Halfak moved this task to Backlog on the Machine-Learning-Team (Active Tasks) board.

Halfak subscribed.

Restricted Application added subscribers: StudiesWorld, Aklapper. · View Herald TranscriptDec 13 2015, 4:50 PM

This is now up on staging. See http://ores-staging.wmflabs.org/scores/wikidatawiki/

@yuvipanda, this change got lumped up with a few new things for ORES, so I'll want to have you somewhat close by when I deploy.

Halfak moved this task from Review to Completed on the Machine-Learning-Team (Active Tasks) board.Dec 14 2015, 2:51 PM

Halfak closed this task as Resolved.Jan 21 2016, 3:42 PM

Halfak set Security to None.

• Phabricator_maintenance removed a subscriber: yuvipanda.Jun 7 2017, 6:45 PM