Zementis is proud to announce PMML 4.1 support

PMML 4.1, the latest version of the Predictive Model Markup Language, is loaded with new and powerful features. 

Zementis is proud to announce support for PMML 4.1 throughout its scoring products, including:

• ADAPA on Site
• ADAPA on the Cloud (Amazon and IBM SmartCloud)
• UPPI for in-database scoring (IBM Netezza, SAP Sybase IQ, EMC Greenplum) 
• UPPI for Hadoop (Datameer).

We have also updated our PMML conversion process so that it now converts PMML files from older versions to version 4.1. In this way, every time a PMML file is presented to ADAPA or UPPI, it is automatically converted to PMML 4.1.

  

Our support for PMML 4.1 includes:

1) Scorecards (including reason or adverse codes and point allocation for complex attributes)

2) Post-processing: you can now transform scores into business decisions as well as output generic data manipulation steps

3) Multiple Models: a powerful and yet simpler way for the expression of model segmentation, composition, chaining and ensemble, which includes Random Forest models

4) Is the model scorable? The "isScorable" flag was added as a way to flag models not destined for production deployment, but that are nonetheless an important part of the model building cycle

5) New built-in functions (for pre- and post-processing).

With this new release and version update, ADAPA and UPPI can be used not only for deployment and execution of predictive solutions, but also for data analysis and processing before model training.

  

If you have any questions about PMML 4.1 and all the features supported in our products, please make sure to contact us or feel free to check out our PMML 4.1 forum for detailed support information.

Agile Deployment of Predictive Analytics on Hadoop: Faster Insights through Open Standards

This joint Datameer/Zementis presentation given at the 2012 Hadoop Summit outlines the benefits of the PMML standard as key element of data science best practices and its application in the context of distributed processing. In a live demonstration, we showcase how Datameer and the Zementis Universal PMML Plug-in (UPPI) take advantage of a highly parallel Hadoop architecture to efficiently derive predictions from very large volumes of data.

Watch it now on YouTube: 

http://www.youtube.com/watch?v=r_g99-kP_BE

Session Abstract:

While Hadoop provides an excellent platform for data aggregation and general analytics, it also can provide the right platform for advanced predictive analytics against vast amounts of data, preferably with low latency and in real-time. This drives the business need for comprehensive solutions that combine the aspects of big data with an agile integration of data mining models. Facilitating this convergence is the Predictive Model Markup Language (PMML), a vendor-independent standard to represent and exchange data mining models that is supported by all major data mining vendors and open source tools (see figure below).

PMML is an XML-based language developed by the Data Mining Group (DMG) which provides a way for applications to define statistical and data mining models and to share models between PMML compliant applications. It provides applications a vendor-independent method of defining models so that proprietary issues and incompatibilities are no longer a barrier to the exchange of models between applications. PMML allows users to develop models within one vendor's application, and use another vendors' applications to visualize, analyze, evaluate or otherwise use the models. Previously, this was very difficult, but with PMML, the exchange of models between compliant applications is now straightforward.

TOP 10 PMML Resources

We offer you a host of free on-line resources that allow you to expand your PMML skills. With these, you can learn how to best operationalize your predictive models, not only on your own infrastructure, but also on the cloud, in-database, or on Hadoop.

Your peers are already communicating predictive analytics with PMML. Learn how you too can benefit from it.

1) BOOK: We have recently published the 2nd edition of our PMML book. Entitled "PMML in Action", the book is available on amazon.com in paperback or in kindle format.

2) BLOGS: Another great resource for PMML related material is the predictive-analytics.info blog site. Besides highlighting the standard itself, this site also discusses the latest PMML support offered by producers and consumers.

3) VIDEOS: We have been busy producing informative webinars with our partners. You can find all our past webinars (including joint webinars with IBM SPSS and Revolution) by visiting our videos page.

4) ARTICLES: White-papers (including joint papers with KNIME and EMC), peer-reviewed articles and invited articles. Check them out! Visit the Zementis articles page.

5) TOOLS: Our tools page contains the description and link to the Transformations Generator, which allows you to graphically design your transformations and export them into PMML.

6) FORUMS: A place to ask questions and discuss model deployment. Explore and join our community forums.

7) EXAMPLES: In the DMG PMML Examples page, you not only can find typical predictive models such as neural networks and decision trees, but also association rules and random forest models.

8) PRESENTATION: Our PMML presentation at LinkedIn earlier this year to the ACM Data Mining Bay Area/SF group is available for on-demand viewing on YouTube. Presentation slides can be donwloaded HERE.

9) NEWSLETTER: The latest information on PMML and model deployment. Our Deploy! Newsletter is now on its 21st issue.

10) GROUP: Last, but not least, you are welcome to join the PMML discussion group in LinkedIn now with close to 3,000 members and growing fast.

Predicting the future ... in four parts

I recently finished writing a four-part article series about predictive analytics entitled Predicting the Future. The topic is near and dear to my heart, since I have been working on the field since my undergrad years back in Brazil (more than 20 years ago). And, lately, through my work with PMML, the Predictive Model Markup Language.

The four articles have just been published by IBM in their entirety in the developerWorks website together with a video in which I introduce each article.



The article themselves can be found here:

1. Predicting the future, Part 1: What is predictive analytics?
2. Predicting the future, Part 2: Predictive modeling techniques
3. Predicting the future, Part 3: Create a predictive solution
4. Predicting the future, Part 4: Put a predictive solution to work

And, if you are interested in learning about open-standards and predictive analytics, I would also recommend the following articles:

• Predictive Analytics in Healthcare: The importance of open standards
• What is PMML? Explore the Power of Predictive Analytics and Open Standards
• Representing predictive solutions in PMML: Move from raw data to predictions

Enjoy!

Webcast: Predictive Analytics on Hadoop

UPDATE: Thanks for your interest in our joint webinar with Datameer: Predictive Analytics on Hadoop. If you were not able to attend or would like to watch it again at your own pace, just click HERE.


To extract value and insight from "Big Data", leading organizations increasingly leverage predictive analytics. By using statistical techniques that uncover important patterns present in historical data, companies are able to predict the future. In doing so, they become more precise, consistent and automated in everyday business decisions.

Please join the Datameer/Zementis webcast entitled Predictive Analytics on Hadoop: Gaining Faster Insights through Open Standards to learn to efficiently derive predictions from very large volumes of structured and unstructured data.

WHEN: Thursday, July 19, 2012, 10:00 am PT / 1:00 pm ET

Free registration 

In this webinar, we showcase the technical capabilities of the Universal PMML Plug-in for Datameer, a solution that combines open standards and Hadoop to reduce complexity and accelerate time-to-market for predictive analytics in any industry and for any business application.

Leave this webinar knowing:

• The benefits of the Predictive Model Markup Language (PMML) standard as a data science best practice for data mining 
• How to leverage predictive analytics in the context of big data 
• How to reduce the cost and complexity of predictive analytics 

 You can register HERE

Synergies and Value Proposition between the R Statistical Package and Zementis ADAPA

The ADAPA Decision Engine provides additional value to all your predictive assets. It is complimentary to R, since it extends your modeling environment into the IT operational domain.

ADAPA® is compatible with R through PMML, the Predictive Model Markup Language, which is the de facto standard to represent predictive models. PMML allows for models to be developed in one application and deployed on another, as long as both are PMML-compliant.

Immediate benefits of using ADAPA

Once a model built in R is saved as a PMML file, it can be directly uploaded in ADAPA. With ADAPA, you can:

• Execute your models independently of R
• Overcome memory and speed limitations imposed by R
• Produce scores in real-time (using Web Services or Java API), on-demand, or batch-mode
• Tap into all the advantages of cloud computing with ADAPA on Cloud (IBM SmartCloud or Amazon EC2)
• Execute your models directly from Excel, by using the ADAPA Add-in for Excel
• Benefit from using other PMML-compliant model development tools such as KNIME and RapidMiner
• Deploy your models in minutes, not months (no need for recoding models into production)
• Manage models via Web Services or a Web console
• Upload one or many models into ADAPA at once
• Use rules to implement model segmentation
• Benefit from the seamless integration of business rules and predictive models through PMML

R PMML support

R offers support for PMML through the R PMML Package available in CRAN. Zementis is a proud contributor to the PMML package which was featured on an article we wrote for The R Journal (to download article, click HERE). The PMML package allows users to export a multitude of predictive models in PMML (for details, click HERE).

We have put together a video which shows how easy it is to export PMML models from R. It uses a simple R script to build a decision tree model using rpart and exports it to PMML using the PMML package. To read posting and watch video, click HERE.

A common industry standard

PMML allows for the de-coupling of two very important modeling phases: development and operational deployment. With PMML, scientists can focus on data analysis and model building using the best of breed model development tools, whereas operational deployment and actual use of the model is made extremely easy and simple with ADAPA.

For example, if a data mining scientist develops a decision tree model using R rpart package, all he/she needs to do to effectively deploy his/her model operationally is to save it as a PMML file and uploaded it in ADAPA. Once in ADAPA, the decision tree model is available for all to use, directly by business users and applications. The model may be used by a business user directly from within Excel to score customers for a marketing campaign.

By doing that, PMML allows for the model development environment to be used just for that, model development. Scoring, real-time or batch-mode from anywhere and at anytime, is handled by ADAPA.