Deriving biased classifiers for better ROC performance

Informatica (Ljubljana)

Volumn 26, Issue 1, 2002, Pages 77-84

  Blockeel, Hendrik ^a   Struyf, Jan ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

Data mining; Machine learning; ROC analysis

Indexed keywords

CLASSIFICATION (OF INFORMATION); DATA REDUCTION; KNOWLEDGE ACQUISITION; TREES (MATHEMATICS);

KNOWLEDGE DISCOVERY;

DATA MINING;

EID: 0036564449     PISSN: 03505596     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (15)

1. Top-down induction of first order logical decision trees
2. The Leuven submission to the Benelearn-99 competition
3. First order models for the predictive toxicology challenge 2001
4. Frankenstein classifiers: Some experiments on the Sisyphus data set
5. Estimating probabilities: A crucial task in machine learning
6. Metacost: A general method for making classifiers cost-sensitive
7. Knowledge discovery in databases: An overview
8. Analysis and visualization of classifier performance: Comparison under imprecise class and cost distributions
9. C4.5: Programs for machine learning
10. Extracting context-sensitive models in inductive logic programming