 |
ML Newsnew | past | best | rss | submit | about |
| BooST: Boosting Smooth Trees for Partial Effect Estimation (arxiv.org) | |
| 2 points by cardosof on Aug 15, 2018 | hide | past | pdf | discuss on HN | |
|
In plain words: It builds a model from trees whose splits fade in gradually instead of snapping on, so you can compute how the prediction shifts as each input changes. On simulated and real data it recovers partial effects, which tree ensembles like Random Forests cannot give. Abstract · BooST: Boosting Smooth Trees for Partial Effect Estimation in Nonlinear RegressionsIn this paper, we introduce a new machine learning (ML) model for nonlinear regression called the Boosted Smooth Transition Regression Trees (BooST), which is a combination of boosting algorithms with smooth transition regression trees. The main advantage of the BooST model is the estimation of the derivatives (partial effects) of very general nonlinear models. Therefore, the model can provide more interpretation about the mapping between the covariates and the dependent variable than other tree-based models, such as Random Forests. We present several examples with both simulated and real data. | |
| add comment on HN |