Unknown attribute values in induction
| Author(s) : | J. R. Quinlan, |
| Publisher : | N/A |
| Publication Date : | 1989 |
| ISSN : | N/A |
| Abstract : | Simple techniques for the development and use of decision tree classifiers assume that all attribute values of all cases are available. Numerous approaches have been proposed with the aim of extending these techniques to cover real-world situations in which unknown attribute values are not uncommon. This paper compares the effectiveness of several approaches as measured by their performance on a collection of datasets., |