There are two ways to
run scoring models in Teradata.
-
You
can create scoring functions for each EM_ output variable. The model
publishing macro creates the scoring functions that are published
as Teradata user-defined functions. These functions can then be used
in any SQL query.
For more information, see Using Scoring Functions to Run Scoring Models.
-
You
can use the SAS Embedded Process. The SAS Embedded Process is a SAS
server process that runs inside the Teradata Enterprise Data Warehouse
(EDW) to read and write data. The model publishing macro creates scoring
files that are then used in a stored procedure to run the scoring
model.
You can create traditional
scoring models by using the SAS Enterprise Miner Score Code Export
node. The SAS Scoring Accelerator for Teradata supports analytic store
scoring. SAS Factory Miner HPFOREST and HPSVM components generate
the analytic store file, the SAS scoring model program, and a format
catalog that are used in analytic store scoring.
The SAS Scoring Accelerator
for Teradata requires a certain version of the Teradata client and
server environment. For more information, see the SAS Foundation system
requirements documentation for your operating environment.