SIRUS: stable and interpretable RUle set for classification (Q2219234)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | SIRUS: stable and interpretable RUle set for classification |
scientific article |
Statements
SIRUS: stable and interpretable RUle set for classification (English)
0 references
19 January 2021
0 references
A new regression rule algorithm called SIRUS is proposed. The main idea of this algorithm is to extract rules from random forests. It is proved that the proposed method enjoys the asymptotic stability. The efficency of the proposed method is illustrated on two popular benchmark datasets.
0 references
classification
0 references
interpretability
0 references
rules
0 references
stability
0 references
random forests
0 references
