Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

Share this Page URL
Help

Appendix A. The Binary Classification Trade-off - Pg. 371

APPENDIX The Binary Classification Trade-off A A binary classification trade-off arises when we wish to classify a set of things into two categories (call them In and Out), but we do not have a direct way of doing the classifying. On the other hand, there is a proxy for those things that is relatively easy to classify. The problem is that the proxy is only approximate. Because it is only approximate, there are four classification outcomes: True positive: The proxy classifies things as In that should be In. True negative: The proxy classifies things as Out that should be Out. False negative: The proxy classifies things as Out that should be In. False positive: The proxy classifies things as In that should be Out.