ECML PKDD 2009 demonstrations are intended as a forum for showcasing the state of the art in machine learning and knowledge discovery software. The focus will be on innovative prototype implementations, systems and technologies in machine learning and data analysis.
We are pleased to announce a call for two types of demonstrations:

(1) On-site demonstrations, and
(2) Stand-alone web demonstrations.

Accepted on-site demonstration papers will be published in the conference proceedings (4 pages). At least one of the authors must register for and attend the conference in order to present the on-site demonstration. Selected on-site demonstrations that can be shown on the web will also be displayed on-line along with the stand-alone web demonstrations.

For the stand-alone web category authors may opt for submitting only an abstract, in which case attending the conference is not a requirement. If such authors submit a paper (4 pages), however, the registration requirement applies.

On-site demonstrations

On-site demonstrations will be presented during a session at the conference. We welcome demonstrations in all application areas, and particularly encourage new applications of machine learning. Example application areas include the following:
Multimodal HCI, Image/video analysis, audio analysis/processing, mobile applications (including games), sensor networks, industrial applications, business intelligence (including visualization), information retrieval, and so on.

Stand-alone web demonstrations

Stand-alone demonstrations will be displayed on the web from the conference time through the end of 2009.

The demonstration should have an accompanying FAQ or Help web page that explains the role of machine learning technology used in the demonstration (either in training or in runtime). These demonstrations may be restricted to mobile phone use, or be in WAP, Flash, AJAX, or other platforms, but they must be accessible to the general public.

Accepted demonstrations will be linked from a special section on the ECML-PKDD website, and will be highlighted in a special session at the conference, where some authors will be asked to give a short presentation.

Web demonstrations will be judged on their novel integration or novel use of machine learning technology, and their suitability for a targeted section of the public. Machine learning may only have been used in an off-line mode, but it must be integral to the success of the demonstration.

Key Dates

• Demonstration submission deadline: May 22
• Demonstration decision notification: June 5
• Demonstration camera-ready: June 12

Submission Information

Submissions will be judged by a committee of technical experts with experience in developing software for machine learning and data analysis. They will select demonstrations based on their technical merits and their interest and usefulness for attendees of the conference.
We strongly recommend that you make your demonstration open source, but do not require this for submission.
On-site demonstrations: Each on-site demonstration should be accompanied by a short paper of at most 4 pages (including figures and screenshots if needed). The paper has to be submitted through the conference paper submission system. The paper must be in English and must be formatted according to the Springer-Verlag Lecture Notes in Artificial Intelligence guidelines. Author instructions and style files can be downloaded at http://www.springer.de/comp/lncs/authors.html.

In this accompanying paper, please try to answer the following questions: What makes your piece of software unique and special? What are the innovative aspects or in what way/area does it represent the state of the art? For whom is it most interesting/useful? (a ML or KDD researcher, a graduate or undergraduate student in these areas, an industrial practitioner, etc.) If there are similar/related pieces of software: What are the advantages and disadvantages compared to the related software?

Stand-alone web demonstrations: Authors should submit an abstract, a URL with the on-line demonstration, and a URL with the FAQ or help page. The demonstration should take no more than 15 minutes to use online, will be accessed by judges between the demonstration submission and acceptance dates, and authors should commit to keep their demonstration running from conference time through to the end of 2009. Authors should submit their demonstration using the on-line submission system. Abstracts for selected stand-alone demonstrations will be published on-line only. Authors to this category can also submit a paper (4 pages), in which case the rules of the on-site demonstrations apply (registration, paper format).

If you would like to submit your demo please visit the following page.

Contact

In case you have any question, please do not hesitate to contact the demonstration chairs at: ecmlpkdd2009-demochairs@ijs.si

• Alejandro Jaimes, Telefónica Research, Madrid, Spain (on-site demonstrations)
• Wray Buntine, NICTA (Australia); Helsinki Institute of IT, Finland (stand-alone demonstrations)

Call for Demos (, 251 KB)