CFP (The 2004 International Workshop on COST-SENSITIVE DATA MINING (CSDM’04)

Call for Papers

The 2004 International Workshop on COST-SENSITIVE DATA MINING (CSDM'04)

June 21-24, 2004, Las Vegas, Nevada, USA


In affiliation with

The 2004 International Conference on Machine Learning: Models, Technologies and 
Application (MLMTA'04)



Aim and Scope

Much of the early work on data mining and machine learning concentrated on 
developing algorithms that focused on classification accuracy.  A more 
challenging and practical problem is to devise algorithms that learn rules or 
associations that optimize income and take better account of costs.  Thus, for 
example, in marketing, we are not simply interested in identifying patterns, 
but actually wish to identify investments that produce greatest income.    

There have been several alternative strategies for developing such 
cost-sensitive learning algorithms, including:  

(a)Meta-models, which provide a generic framework that operate over arbitrary 
algorithms

(b)Adaptation of existing algorithms and metrics to incorporate costs

(c)Use of Genetic algorithms, Neural Networks and Bayesian Networks to evolve 
cost-sensitive decision trees

This workshop aims to bring together researchers and practitioners working on 
this important and growing research area.  

Topics of Interest

- Cost-Sensitive associative rule mining
- Cost-Sensitive classification
- Cost-Sensitive clustering
- Use of uncertainty and fuzzy models for optimizing profit
- Visualization of cost-sensitive rules
- Model and taxonomies of time/cost and space/cost
- Evaluative and comparative studies i.e. cost .vs. time .vs. accuracy
- Practical applications of cost-sensitive mining including medical diagnosis, 
financial, industrial       production processes, machinery diagnosis and 
automated testing of electronics, e-marketing, etc. 

Format

The workshop will consist of 
- Invited talks by recognized researchers and practitioners 
- Presentations based on contributions submitted by participants 
- Discussions 

In order to increase participation by all attendants, we will 

- Request a position statement from participants, indicating  their background, 
experience, and interest in the topic 
- Prepare a set of discussion topics for the general discussions 
- Initiate the publication of selected contributions, e.g. via a special issue 
in a journal
- Contributions will be made available to participants prior to the workshop 
through a Workshop Web page. 

Submission Guidelines

Research papers (up to 7 pages in IEEE-style) as well as short research papers 
(up to 4 pages in IEEE-style) should be submitted electronically in either 
word, .ps or .pdf format and sent to  
(s.vadera-kOSiIr09Tbc2EctHIo1CcQ@xxxxxxxxxxxxxxxx)  or 
(m.saraee-kOSiIr09Tbc2EctHIo1CcQ@xxxxxxxxxxxxxxxx). At least one author of each 
paper is expected to participate in the workshop and present his/her work. 

Important Dates
 
- 16 February 2004: Submit title and abstract
- 1 March, 2004:    Submit paper for review
- 19 March 2004:          Notification of acceptance. 
 
 

WORKSHOP ORGANIZATION

 Workshop co-Chairs

   Professor Sunil Vadera, University of Salford. UK.
   Dr Mohamad Saraee, University of Salford, UK

Organising Committee
   Professor Sunil Vadera, University of Salford. UK
   Dr Mohamad Saraee, University of Salford, UK
   Dr Farid Meziane,  University of Salford, UK


Program Committee 

 Professor Paul Chung, University of Loughborough, UK
 Dr Mahesh Joshi, IBM Almaden Research Center, USA
 Professor John Keane, UMIST, UK.
 Dr Matjaz Kukar, University of Ljubljana, Slovenia
 Dr Christophe Marsala, Pierre et Marie Curie, Paris VI, LIP6
 Professor Elisabeth Métais, Conservatoire National des Arts et Metiers de 
Paris, France
 Dr Samia Nefti-Meziani, University of Salford, UK
 Dr Andres Rodriguez,   Instituto de Investigaciones Eléctricas, Mexico 
 Professor Enrique Sucar, Tecnológico de Monterrey, Cuernavaca, Mexico
 Dr Babis Theodoulidis, UMIST, UK.
 Dr Bianca Zadrozny, IBM T. J. Watson Research Center, USA


--------------------------------------------------------------------------
To subscribe or unsubscribe yourself from
dbworld, send a msg to majordomo-hcNo3dDEHLuVc3sceRu5cw@xxxxxxxxxxxxxxxx with 
one of these lines:
subscribe dbworld OR unsubscribe dbworld
To find out more options send a msg with the line:
help
To post messages, go to URL www.cs.wisc.edu/dbworld
--------------------------------------------------------------------------