| Literature DB >> 10636944 |
Abstract
In this note we use examples from the literature to illustrate some poor practices in assessing the performance of supervised classification rules, and we suggest guidelines for better methodology. We also describe a new assessment criterion that is suitable for the needs of many practical problems.Mesh:
Year: 2000 PMID: 10636944 DOI: 10.1162/089976600300015808
Source DB: PubMed Journal: Neural Comput ISSN: 0899-7667 Impact factor: 2.026