Ground Truth Jobs
Estimate ground truth queries using click signals and query signals, with document relevance per query determined using a click/skip formula.
| Pair this job with the Ranking Metrics job to calculate relevance metrics, such as nDCG. |
Use this job when you want to estimate ground truth queries using click and query signals with document relevance per query determined using a click/skip formula. Pair this job with ranking metrics job to calculate relevance metrics, such as nDCG
id - stringrequired
The ID for this Spark job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_)
<= 128 characters
Match pattern: ^[A-Za-z0-9_\-]+$
signalsCollection - stringrequired
Collection containing click signals and the associated search log identifier
>= 1 characters
searchLogsAddOpts - object
Additional options to use while loading search logs collection
signalsAddOpts - object
Additional options to use while loading signals collection
searchLogsPipeline - string
Pipeline id associated with search log entries
>= 1 characters
joinKeySearchLogs - string
Join key of query signals in the signals collection
Default: id
joinKeySignals - string
Join key of click signals in the signals collection
Default: fusion_query_id
filterQueries - array[string]
Filter queries to apply while choosing top queries from query signals in signals collection
topQueriesLimit - integer
Total number of queries to pick for Ground truth calculations
Default: 100
type - stringrequired
Default: ground_truth
Allowed values: ground_truth