You can use SAS Scoring
Accelerator in conjunction with the SAS Model Manager to manage and
deploy scoring models in DB2, Greenplum, Netezza, and Teradata.
The
Publish
Scoring Function of SAS Model Manager enables you to
publish models that are associated with the DATA Step score code type
to a configured database. When you publish a scoring function for
a project, SAS Model Manager exports the project's champion model
to the SAS Metadata Repository. The SAS Scoring Accelerator then creates
scoring functions in the default version that can be deployed inside
the database based on the project's champion model score code. The
scoring function is validated automatically against a default train
table to ensure that the scoring results are correct. A scoring application
or SQL code can then execute the scoring functions in the database.
The scoring functions extend the database's SQL language and can be
used in SQL statements like other database functions.
In the August 2012 release,
you can also use the SAS Scoring Accelerator and SAS Model Manager
to import
SAS/STAT linear models and SAS High-Performance Analytics
models from a SAS package file (.SPK). Models that have a DATA step
score code type can be scored, published, and included in performance
monitoring.