DOE OSTI · code-56049
iRF v2.0
Abstract
A predictive, stable, and interpretable machine learning tool: the iterative random forest algorithm (iRF). iRF discovers high-order interactions among variables with the same order of computational cost as random forests (RF). We have demonstrated the utility of iRF in several applications in the biological and environmental sciences. It is a general purpose machine learning framework for building "explainable" predictive engines.
Keep this discovery
Explore connections, maps & timelines
Brown, JamesB., Basu, Sumanta, Kumbier, Karl, Yu, Bin. 2021-02-23. iRF v2.0. https://doi.org/10.11578/dc.20210429.3
Cite the original work for its findings. Save a collection to share your selection of sources.