Using multiple and negative target rules to make classifiers more understandable

Jiuyong Li, Jason JonesKnowledge-Based Systems 2006 · DOI · OpenReview

Abstract

One major goal for data mining is to understand data. Rule based methods are better than other methods in making mining results comprehensible. However, current rule based classifiers make use of a small number of rules and a default prediction to build a concise predictive model. This reduces the explanatory ability of the rule based classifier. In this paper, we propose to use multiple and negative target rules to improve explanatory ability of rule based classifiers. We show experimentally that this understandability is not at the cost of accuracy of rule based classifiers.
BibTeX
@article{li2006using,
  author = {Jiuyong Li and Jason Jones},
  title = {{Using multiple and negative target rules to make classifiers more understandable}},
  journal = {Knowledge-Based Systems},
  year = {2006},
  doi = {10.1016/j.knosys.2006.03.003},
}

Loading related content...

Figure