In conjunction with IEEE ICDM 2012 in Brussels, December 10 2012

Most real world applications need to take account of costs, whether it is the cost of obtaining data, costs associated with  applying a data mining algorithm or the  financial and legal implications of misclassification.   Thus, for example, in marketing, we are interested in identifying investments that produce greatest income given the cost of marketing. In medical diagnosis we need to take account of the costs of tests required in diagnosis,
such as blood tests, x-rays and scans.
 
This workshop includes papers that explore topics such as learning rules that take account of  costs of misclassification, cost sensitive unsupervised learning,   the use of utility and game theory in balancing costs and benefits,  active learning for minimising costs of acquiring information and even how to take account of costs when they are missing.  The workshop will provide a useful opportunity to understand some of the key issues in cost sensitive data mining and current direction of research in this field.
 

Programme: Turner Room, 14:00 to 18:00

 

14:00:14:10    Welcome and Introduction, Sunil Vadera

 

14:10:14:40    Invited Talk: Cost Sensitive Action Rule Mining, Hendrik Blockeel

 

14:40-15:05    A Weighted SOM for classifying data with instance-varying importance, Peter Sarlin

 

15:05-15:30    When Additional Views Are Not Free: Active View Completion for Multi-View Semi-Supervised Learning,

                          Brian Quanz and Jun Huan

 

15:30-16:00    Coffee Break

 

16:00-16:25    A Multi-Armed Bandit Approach to Cost-Sensitive Decision Tree Learning

                          Susan Lomax, Sunil Vadera, Mohamad Saraee

 

16:25-16:50    Learning in the Class Imbalance Problem When Costs are Unknown for Errors and Rejects

                          Xiaowan Zhang and Baogang Hu

 

16:50-17:15    Learning Cost-Sensitive Rules for Non-Forced Classification, Arjun Bakshi and Raj Bhatnagar

 

17:15-17:40    Towards Utility Maximization in Regression, Rita P. Ribeiro

 

17:40-18:00      Discussion and Closing Remark

 

Organising Committee

Programme Committee

  • Charles Elkan, University of California, San Diego
  • Wei Fan, IBM
  •  John Keane, University of Manchester
  • Dragos Margineantu, Boeing Research & Technology
  • Farid Meziane, University of Salford
  •  Goran Nenadic, University of Manchester
  • Victor Sheng, University of Central Arkansas
  • Kevin Small, University of Tufts
  •  Oksana Yakhnenko  from Google, USA
  •  Shipeng Yu, Siemens Medical Solutions, USA