CFP

IDDM-2002
2nd International Workshop on
Integration and Collaboration Aspects of
Data Mining, Decision Support and Meta-Learning

http://ecmlpkdd.cs.helsinki.fi/iddm-2002.html

This workshop will be held in conjunction with ECML/PKDD-2002, Helsinki, Finland, 19-23 August, 2002 (http://ecmlpkdd.cs.helsinki.fi/). It is a follow-up to the successful IDDM-2001 workshop held in Freiburg (see http://www.cs.bris.ac.uk/~cgc/ECML-PKDD01/cfp.html).

Workshop Topics and Goals

This workshop addresses the integration and collaboration aspects of Data Mining (DM), Decision Support (DS) and Meta-Learning (ML). In particular, this workshop is aimed at trying to upgrade the corresponding approaches and methodologies, such as CRISP-DM, through contributions, addressing the following issues:

Combining Data Mining with Decision Support

DM has the potential of solving DS problems, for example when previous decisions have been recorded as data to be used for analysis with DM tools. On the other hand, DS methodology usually results in a decision model, reflecting expert knowledge of decision makers. How can such expert knowledge be incorporated into problem solutions by DM? Can it be used as background knowledge in relational data mining? Can such expert knowledge be induced automatically? Are there any systematic methodological means of combining the two approaches to problem solving? How can DM benefit from DS models, especially in cases where the data available for mining is incomplete or of insufficient quality?

Collaborative Data Mining

Usually, DM tasks are solved by a single individual or group of individuals working jointly on a problem. However, with the Internet and advances of group support methodologies and tools, DM tasks could be solved through a collaboration of different groups of researchers at different sites. Novel ideas, reviews of existing approaches, or different modes of collaboration should be explored (e.g., competitive vs. collaborative), and issues addressed such as infrastructure and methods for supporting distant collaborative work (e.g., how to integrate new individuals/groups following the start/stop-any-time principle).

Combining Results of Classifiers, Meta-Learning, etc.

Here, the emphasis is on novel ideas and/or reviews of existing approaches to model selection, model combination, model representation and all issues relevant to learning to learn (e.g., landmarking, performance prediction, knowledge transfer, data characterisation, meta-data collection and exploitation, standardised experimental setups/methods, etc).

Relational Data Mining

Most data in standard DM has the form of a single relational table. What if data is stored in multiple relational tables? Thus, how to combine the results of mining separate relational tables? A standard approach in ILP is to consider one table as the master data table, and all others as tables providing background knowledge. What if this is not natural? Would mining of individual tables and combining results be a better solution? Are there other approaches to this problem?

DM, DS, and ML Integration: Methodological, Technical, and Standardization Aspects

This theme includes, but is not limited to, the following topics:

• ML tools for classifier and model selection
• ROC methodology for DM, DS and ML
• Data pre-processing tools and methods for DM and DS
• Representation languages for DM and DS models
• Standards supporting the exchange of DM and DS models for different applications and visualization tools, such as PMML (Predictive Model Markup Language)
• DS shells that seamlessly integrate models developed by DM
• Shared ontology and methodology for solving DM and DS problems

This workshop is aimed at both researchers and practitioners in Data Mining, Decision Support, and Meta-Learning. It is expected that there will be contributions from the main European research Consortia whose work focuses on the above topics (e.g., METAL, Sol-Eu-Net, KDNet, etc).

Participants will gain a better appreciation of the issues facing the application and deployment of DM, DS, and ML solutions in the real world. New ways of working together and combining results will be discussed, fostering further collaboration between participants' organisations. It is hoped that, as a result of this workshop, more people will work together more often, more effectively and in more sensible ways.

Paper Submission

Papers are invited addressing one or more of the topics presented above. Papers should be prepared according to ECML/PKDD-2002 Instructions for Authors (http://ecmlpkdd.cs.helsinki.fi/ifa.html), and should not exceed 12 pages. Acceptable formats are PostScript or PDF.

Please send the papers by e-mail to marko.bohanec@ijs.si, cc: branko.kavsek@ijs.si

Each paper will be reviewed by at least two reviewers. Accepted papers will be published in the workshop proceedings and on the WWW.

Important Dates

Paper submission: 24 May 2002
Notification of acceptance: 14 June 2002
Camera-ready version: 1 July 2002
Workshop at PKDD/ECML 2002: 19 or 20 August 2002 (to be announced)

Workshop Chairs

Marko Bohanec (marko.bohanec@ijs.si)
Dunja Mladenic (dunja.mladenic@ijs.si)
Nada Lavrac (nada.lavrac@ijs.si)