You can use SAS Scoring
Accelerator in conjunction with SAS Model Manager to manage and deploy
scoring models in DB2, Greenplum, Hadoop, Oracle, Netezza, SAP HANA,
and Teradata.
SAS Model Manager enables
you to publish to a configured database the project champion model
and challenger models that are associated with the DATA Step score
code type. SAS Model Manager uses the SAS Scoring Accelerator and
SAS/ACCESS interface to the database to publish models to the database.
The Scoring Accelerator takes the models from SAS Model Manager and
translates them into scoring files or functions that can be deployed
inside the database. After the scoring functions are published using
the SAS/ACCESS interface to the database, the functions extend the
database’s SQL language and can be used in SQL statements such
as other database functions. After the scoring files are published,
they are used by the SAS Embedded Process to run the scoring model.
You can also use SAS
Model Manager to import SAS Enterprise Miner models, SAS/STAT linear
models, and SAS High-Performance Analytics models from a SAS package
file (.SPK), and you can import PMML models from a PMML model file.
Models that have a DATA step score code type can be scored, published,
and included in performance monitoring. With the fourth maintenance
release of SAS 9.4, users can import analytic store models from a
SAS analytic store file (SASAST). Analytic store models that are registered
from SAS Factory Miner to the SAS Model Manager model repository or
that are imported into SAS Model Manager from a SAS analytic store
file can be published to Hadoop or Teradata. Publishing analytic store
models from SAS Model Manager to SAP Hana is not supported yet. They
can also be scored and included in performance monitoring or reports.