Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Out-of-Sample Evaluation

Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_621


Out-of-sample evaluation refers to  algorithm evaluation whereby the learned model is evaluated on  out-of-sample data. Out-of-sample evaluation provides an unbiased estimate of learning performance, in contrast to  in-sample evaluation.

Cross References

Copyright information

© Springer Science+Business Media, LLC 2011