A zero altered Poisson random forest model for genomic-enabled prediction
Montesinos-Lopez, O.A.
A zero altered Poisson random forest model for genomic-enabled prediction - Bethesda, MD (USA) : Genetics Society of America, 2021.
Peer review Open Access
In genomic selection choosing the statistical machine learning model is of paramount importance. In this paper, we present an application of a zero altered random forest model with two versions (ZAP_RF and ZAPC_RF) to deal with excess zeros in count response variables. The proposed model was compared with the conventional random forest (RF) model and with the conventional Generalized Poisson Ridge regression (GPR) using two real datasets, and we found that, in terms of prediction performance, the proposed zero inflated random forest model outperformed the conventional RF and GPR models.
Text in English
2160-1836 (Online)
https://doi.org/10.1093/g3journal/jkaa057
Marker-assisted selection
Data
Plant breeding
Models
A zero altered Poisson random forest model for genomic-enabled prediction - Bethesda, MD (USA) : Genetics Society of America, 2021.
Peer review Open Access
In genomic selection choosing the statistical machine learning model is of paramount importance. In this paper, we present an application of a zero altered random forest model with two versions (ZAP_RF and ZAPC_RF) to deal with excess zeros in count response variables. The proposed model was compared with the conventional random forest (RF) model and with the conventional Generalized Poisson Ridge regression (GPR) using two real datasets, and we found that, in terms of prediction performance, the proposed zero inflated random forest model outperformed the conventional RF and GPR models.
Text in English
2160-1836 (Online)
https://doi.org/10.1093/g3journal/jkaa057
Marker-assisted selection
Data
Plant breeding
Models