Material Detail

Cost-Sensitive Multi-class Classification from Probability Estimates

Cost-Sensitive Multi-class Classification from Probability Estimates

This video was recorded at 25th International Conference on Machine Learning (ICML), Helsinki 2008. For two-class classification, it is common to classify by setting a threshold on class probability estimates, where the threshold is determined by {ROC} curve analysis. An analog for multi-class classification is learning a new class partitioning of the multiclass probability simplex to minimize empirical misclassification costs. We analyze the interplay between systematic errors in the class probability estimates and cost matrices for multi-class classification. We explore the effect on the class partitioning of five different transformations of the cost matrix. Experiments on benchmark datasets with naive Bayes and quadratic discriminant analysis show the effectiveness of learning a new partition matrix compared to previously proposed methods.


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.