After the good results in T189843 we ran the same test on 18 wikis this time. AB test was run for T187148 from 20180329 through 20180419. The data is stored in HDFS as the SearchSatisfaction schema.
We ran 3 standard buckets:
control - The currently deployed ML ranker
classic - The classic non-ML ranker
explorer - The new ranker under test
We also ran 2 interleaved buckets:
control-explorer-i: control in A, explorer in B
classic-explorer-i: classic in A, explorer in B