.png){kind=icon}
Return
Variable selection using relative importance rankings
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113561.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Novel variable selection using Relative Importance (RI) is proposed and evaluated. • A computationally efficient RI is developed and applied to variable selection. • RI-based methods outperform the lasso and other benchmarks in challenging cases. • RI-based methods are superior in cases with highly correlated noisy predictors. • Experiments on gene expression data confirm the method’s scalability and accuracy.
Keywords:
Relative Importance
Variable Selection
Lasso
Correlated Predictors
Gene Expression Data
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available
Cited Papers
No cited papers available