Recommender¶
The Recommender Operator is a low-code template built around the Surprise SVD algorithm for collaborative filtering use cases. It currently focuses on matrix factorization scenarios, and additional capabilities will be documented as they become available.
Current Capabilities¶
Data inputs: expects three tabular sources named
users,items, andinteractions. Each source can be loaded from local files, OCI Object Storage (oci://URIs), or database queries using the standard ADSInputDataconfiguration.Model: wraps Surprise
SVDwith sensible defaults.spec.model_nameis reserved for future extensibility and is pinned tosvdinternally.Outputs: generates a recommendations CSV (
recommendations.csvby default) and, when enabled, an HTML summary report.Configuration essentials:
top_k,user_column,item_column, andinteraction_columnare mandatory and map your datasets to the operator.Deployment targets: supports local execution and OCI Data Science Jobs; see Quick Start for the CLI flow and Scalability for production guidance.
Future Updates¶
New capabilities—such as alternative algorithms, advanced tuning controls, or expanded deployment guidance—will be documented in this guide as they are released.
Added in version 2.11.14.