|Predictive Analytics for Big Data|
|Vendor-neutral Depoloyment with PMML|
Not all analytic tasks are born the same. If one is confronted with massive volumes of data that need to be scored on a regular basis, in-database scoring sounds like the logical thing to do. In all likelihood, the data in this case is already stored in a database and, with in-database scoring, there is no data movement. Data and models reside together hence scores and predictions flow on an accelerated pace.
A new day has come!
Zementis is now offering UPPI™ (Universal PMML Plug-in), an amazing PMML-based Scoring Engine for in-database scoring.
For starters, it won't break your budget (feel free to contact us for details). Also, it is simple to deploy and maintain. UPPI was designed from the ground up to take advantage of efficient in-database execution. Last but not least, as its name suggests, it is PMML-based. PMML, the Predictive Model Markup Language is the standard for representing predictive models currently exported from all major commercial and open-source data mining tools. So, if you build your models in either SAS, IBM SPSS, or R, you are ready to start benefiting from in-database scoring right away
UPPI seamlessly embeds models within your database. Data scoring requires nothing more than adding a simple function call into your SQL statements. You can score data against one model or against multiple models at the same time. There is no need to code regression equations or other more complex calculations in SQL or stored procedures. PMML and UPPI can easily take care of that.
Modeling techniques currently supported are:
|• Association Rules
• Decision Trees for classification and regression
• Neural Network Models: Back-Propagation, Radial-Basis Function, and Neural-Gas
• Support Vector Machines for regression, binary and multi-class classification
• Linear and Logistic Regression (binary and multinomial)
• Naïve Bayes Classifiers (with support for continuous input variables)
• General and Generalized Linear Models
• Cox Regression Models
• Rule Set Models
• Restricted Boltzmann Machines
• Clustering Models: Distribution-Based, Center-Based, and 2-Step Clustering
• Scorecards (including support for reason codes and point allocation for categorical,
continuous and complex attributes)
• Multiple Models: Model Composition, Segmentation, Chaining, Cascade and Ensemble,
including Random Forest Models and Boosted Trees
In addition to all these predictive techniques, UPPI accepts PMML models of all versions (2.0, 2.1, 3.0, 3.1, 3.2, 4.0, and 4.1) generated by any of the major commercial and open source mining tools (SAS, IBM SPSS, STATISTICA, MicroStrategy, Microsoft, Oracle, KXEN, Salford Systems, TIBCO Spotfire, R, KNIME, RapidMiner, etc.). It does not get more universal than this!
Start accelerating your scoring today with the Universal PMML Plug-in from Zementis!