More accurately described as precision–recall BEP, it is an evaluation measure originally introduced in the field of information retrieval to evaluate retrieval systems that return a list of documents ordered by their supposed relevance to the user’s information need (see also Document Classification). It can also be used to evaluate any classification model f that addresses a two-class classification problem but outputs real-valued predictions f(x) instead of binary ones. To use such a classifier in practice, one would select a threshold θ and predict an instance x to be positive if f(x) > θ and negative otherwise. Thus, the precision and recall of this system depend on the choice of the threshold θ. A lower threshold means higher recall, but usually also lower precision. At some point (when the number of instances predicted to be positive is the same as the actual number of positive instances), precision and recall are equal; this value of precision and recall is known as the precisio...
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsEditor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media New York
About this entry
Cite this entry
(2017). Breakeven Point. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_937
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7687-1_937
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7685-7
Online ISBN: 978-1-4899-7687-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering