ADAPA Add-in for Excel 2007 - On-Line Video Tutorial is Now Available!

The ADAPA Add-in for Excel 2007 has been a great success story for Zementis. Many Excel users have already benefited from the add-in and are finding out how easy it is to finally have predictive analytics at their fingertips.

To help users get the most out of the add-in and to demo its capabilities, we have put together a video that shows the scoring of 3 data sets which are made available together with the add-in. You can decide to to watch the video in high resolution or in YouTube. Just click the appropriate link below.



High Res. Video: ADAPA Add-in for Excel





YouTube Video: ADAPA Add-in for Excel



The real power of the add-in however falls on its ingenious use of ADAPA on the Cloud. Users can now sign-up for ADAPA with Amazon (as easy as buying a book) and deploy their models which they can then easily access in Excel by following some simple steps.

This is yet another way for ADAPA users to fully realize the power of their predictive models.

For more information on the ADAPA Add-in, please feel free to take a look at our other add-in posts:

• Add-in announcement
  


• Scoring data in 4 steps (how to score)
  


• Sample data sets and models (what comes with the demo ADAPA instance)
  


• Help in setting up connection (using your own ADAPA instance and models)
  


• Help in applying model (mapping data to model inputs)
  

ADAPA 2.20 Released: Enhanced PMML Support and Improved Web Console.

Zementis is constantly adding new features to ADAPA. In its latest 2.20 release (February 2, 2010), it adds important new features with automatic PMML conversion, model composition, and an improved Web Console experience.




Integrated PMML Converter (and Corrector)

With this release, the popular PMML Converter has been incorporated seamlessly into ADAPA. As a result, ADAPA can now directly import older PMML versions. You may be already aware that many of the modeling tools still export older versions of PMML. Now, you can directly import these older versions of PMML into ADAPA without having to manually upgrade them externally. In addition, we have added functionality to automatically correct a number of common problems found in PMML generated by some popular modeling tools, allowing the models to work as intended.

Remember that we recommend that you always run a score matching test to validate the imported models against your data and modeling environment. And if you find that we still missed something in our PMML converter/corrector, do let us know.


Model Composition

ADAPA now supports composing of multiple models into a single model. This important feature supports a variety of model composition cases such as model selection or segmentation, model sequencing, and value post-processing. For examples and instructions on how to represent model composition in PMML and ADAPA, please refer to the ADAPA Predictive Analytics Guide available for download from the ADAPA Console Help page.

Web Console

The ADAPA Web Console now allows you to download any of the imported models. This feature makes it easy to review your models, including any warning messages generated during the import. In addition, given that all imported models are automatically converted, the download feature allows you to retrieve and review the upgraded (and possible corrected) version of your model.

For more information on this exciting new feature, please feel free to contact us.

"Blue washing" our cities using PMML ...

If you have not seen this week's article on Newsweek by the chairman and CEO of IBM, you should most definitely take a look at it.

Granted, we as humans are moving more and more to cities (think of China) and so as discussed in the article by 2050, 70% of us will be leaving in cities. This brings several thoughts into mind ... but what IBM is interested on is data and advanced analytics "to make sense of it all". Data is envisioned to come more and more from sensors in our roadways, rivers (water flow and pollution monitoring), bridges, buildings, as well as other sources cited in the article such as health-care and education.

But how can we make sense of it all? As highlighted in the Newsweek article, by bringing standards to the table. If we together as a nation and as humans are to benefit from the intelligence inherent to all this data, agreeing on standards is a must. Think of the Xmas day plot that turned into a data fiasco ... lots of data in different formats and places, but no intelligence or connectivity.

Standards such as PMML (Predictive Model Markup Language) which allows for predictive analytics models as well as data pre- and post-processing to be moved between analytical tools is not only a great example of companies getting together to make the move in the right direction, but also something to be celebrated. IBM has been part of the DMG (Data Mining Group), the committee shaping up PMML for many years now. Other companies such as SAS, Microstrategy, Equifax, and Zementis are also part of the commitee as well as open-source companies such as KNIME and Rapid-I.

IBM is betting on advance analytics and standards ... as so are we!

Integrating predictive models into SAP applications using ADAPA

In an article recently posted on the SAP Developer Network, Albrecht Weiss describes how to integrate predictive models into SAP applications. The article provides step-by-step instructions to deploy, integrate and execute predictive models based on SAP and Zementis ADAPA.


First, a predictive model is built using the SAP BusinessObjects Predictive Workbench and exported into PMML (Predictive Model Markup Language). The PMML model is then easily deployed using ADAPA on the Cloud and details are given for executing the model using Web Services from inside SAP using ABAP.

The exchange of models between applications is only possible because of PMML since it allows for predictive models (and data manipulation) to be represented in a concise, clear, and standard way. As a matter of fact, PMML is the de facto standard to represent predictive models and is currently supported by the top analytics tools, including SAP BusinessObjects Predictive Workbench and ADAPA.

Click HERE for Albrecht's SAP/ADAPA article.

ADAPA 2.19 released. New and improved Web Services functionality.

Zementis is constantly adding new features to ADAPA. In its latest 2.19 release (November 30, 2009), it adds an important new feature that significantly enhances bulk scoring of large data sets: scoring of CSV files through web service calls.

With this new feature, an application can now submit for scoring input data compiled in a CSV file (ADAPA already supported SOAP XML format).

As an example, a simple application can export datafrom a database into a file, score the file, and import the results back into the database. And, much like the other web services, the file can be scored against multiple models in a single web service call, saving unnecessary round trip messages.

With CSV being a more compact data format over the SOAP XML representation, this can lead to significant savings in the volume of data being exchanged. In addition, the CSV file can even be submitted in a compressed format to minimize the network transfer time overhead.

For more information on this exciting new feature, please feel free to contact us.