Items-for-user recommendations use the Recommend Items for User query stage to present items that are similar to ones in which the user has previously shown interest, based on the user’s search history, browsing history, purchase history, and so on. This is one type of collaborative recommendation.
If you have enabled signals and recommendations for a collection, then two default jobs are already created and configured to produce items-for-user recommendations (as well as items-for-item recommendations):
<collection>_item_recommendations, an ALS Recommender job
<collection>_bpr_item_recommendations, a BPR Recommender job
This is the recommended job type; it produces better results with a shorter runtime than the ALS job. Download the
APPName_item_item_rec_pipelines_bpr.jsonfile and import it to create the query pipeline that consumes this job’s output. See Fetch Items-for-User Recommendations (Collaborative/BPR Method) for details.