Operational deployment of predictive solutions includes exporting the data mining models you built in SAS, IBM SPSS, STASTISTICA, KNIME, R, ... into PMML, the Predictive Model Markup Language. Once in PMML standard, these models can be easily moved into production: on-site, in the cloud, Hadoop or in-database. Zementis offers a range of products that make this possible. These include the ADAPA Decisioning Engine and the Universal PMML Plug-in. Besides providing a predictive analytics engine, ADAPA also encapsulates a rules engine which allows for predictive models to be seamlessly integrated with business rules.
In this demo, we show a pre-qualification app
that uses predictive models and rules to analyze the risk of mortgage
default on loan applications. An application is accepted or referred for
a variety of loan products depending on its perceived risk. ADAPA is
the engine driving this application in the back-end.
Once logged in
we use the ADAPA Web to download the mortgage
solution files which are used throughout the demo. Predictive models
expressed in PMML format are uploaded and verified in ADAPA along
with rulesets expressed in tabular format. The ADAPA Web Console is used
for managing predictive models, rulesets, and resource files as well as
for batch-scoring. Real-time scoring is obtained via web-services or
the Java API.
Finally, we show how the ADAPA Add-in
for Excel is used to score data directly from within Excel. This part of
the demo features the scoring of loan and tax data as well as the
visualization of results via dashboards.
Post a Comment