2021
DOI: 10.3390/math9050579 View full text |Buy / Rent full text
|
|

Abstract: A boosting-based machine learning algorithm is presented to model a binary response with large imbalance, i.e., a rare event. The new method (i) reduces the prediction error of the rare class, and (ii) approximates an econometric model that allows interpretability. RiskLogitboost regression includes a weighting mechanism that oversamples or undersamples observations according to their misclassification likelihood and a generalized least squares bias correction strategy to reduce the prediction error. An illust… Show more

Help me understand this report

Search citation statements

Order By: Relevance
Select...
1
0
1
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

0
1
0
Order By: Relevance
“…We shall also investigate the effect of adding physiologic risk predictors (e.g., vital signs, laboratory values) from other data sources which were not available to us at the time of these analyses. We shall also explore other interaction methods proposed by (Elmes et al, 2021), (Pesantez-Narvaez et al, 2021) and (Tomz et al, 2001) to address rare event issues.…”
Section: Model Performancementioning