A Simple Rule for Monitoring the Error Rate of Random Forest for Classification
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Statistics are proposed to assist in choosing the number of trees in random forests for classification, one of which is very useful in monitoring of the out-of-bag (OOB) error rate. These statistics are used sequentially as the forest is constructed and are computed from OOB votes or test set votes. They provide a measure of the expected disagreement between the current forest and the limiting forest with infinitely many trees. Examples and simulation studies of the statistic for monitoring of the OOB error rate are provided to illustrate the performance of these statistics.
Abstract
Statistics are proposed to assist in choosing the number of trees in random forests for classification, one of which is very useful in monitoring of the out-of-bag (OOB) error rate. These statistics are used sequentially as the forest is constructed and are computed from OOB votes or test set votes. They provide a measure of the expected disagreement between the current forest and the limiting forest with infinitely many trees. Examples and simulation studies of the statistic for monitoring of the OOB error rate are provided to illustrate the performance of these statistics.
참고문헌 (9)
- Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)
- Hernández-Lobato D, "How large should ensembles of classifiers be", Pattern Recogn, 46, pp.1323~1336 (2013)
- Lopes, ME, "Estimating the algorithmic variance of randomized ensemble via the bootstrap", Ann Stat, 47, pp.1088~1112 (2019)
- Hernández-Lobato D, "Inference on the prediction of ensembles of infinite size", Pattern Recogn, 44, pp.1426~1434 (2011)
- Banfield RE, "A comparison of decision tree ensemble creation techniques", Ieee T Pattern Anal, 29, pp.173~180 (2007)
- "UCI machine learning repository" (2010)[URL]
- Leisch F, "mlbench: Machine learning benchmark problems. R package version 2.1-0", ~ (2010)
- Liaw A, "Classification and regression by random-Forest", R News, 2, pp.18~22 (2002)
- "Random forests 5.1" (2004)[URL]