Legacy Item Recommender Jobs
Compute user recommendations based on a pre-computed item similarity model.
Use this job when you want to compute user recommendations based on pre-computed item similarities.
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_\-]+$
trainingCollection - stringrequired
User/Item preference collection (often a signals collection or signals aggregation collection)
itemSimCollection - stringrequired
Collection containing item-to-item similarity values (computed by any means)
outputRecsCollection - stringrequired
Collection containing item-to-item similarity-based recommendations
trainingDataFilterQuery - string
Solr query to filter user preferences
Default: *:*
prefUserIdField - string
Solr field name containing stored user ids in the preference collection
Default: user_id_s
prefItemIdField - string
Solr field name containing stored item ids in the preference collection
Default: item_id_s
prefWeightField - string
Solr field name containing preference weight in the preferences collection
Default: weight_d
itemSimQuery - string
Solr query to filter item similarities (e.g. to filter by similarity type, or algorithm id)
Default: *:*
simItemIdField - string
Solr field name containing stored item ids in the item-similarity collection
Default: item_id_s
simOtherItemIdField - string
Solr field name containing the ids for the *other* item similar to the main item
Default: other_item_id_s
simSimField - string
Solr field name containing item-item similarity value in the item-similarity collection
Default: sim_d
numRecsPerUser - integer
Limit on the maximum number of recommendations to compute per user
Default: 10
type - stringrequired
Default: item_similarity_recs
Allowed values: item_similarity_recs