I have a modeling framework with an outcome that must necessarily be positive. In the training data, the outcome ranges from close to zero to much higher (approximately 0.05 to 100). Is there a way to fit a random forest model for positive outcomes? Prediction accuracy is important in this problem, and I want to model the data with more flexible, nonparametric methods like random forests.
Asked
Active
Viewed 66 times
3
-
1A Random Forest can not predict outside of the range of your target variable. This is why trees are typically looked down upon when there is a significant trend for example in time series. – Tylerr May 10 '21 at 13:55
1 Answers
3
Random forest does this by default. Random forest predictions are the average of the terminal node values. The average of nonnegative values is also nonnegative.

Sycorax
- 76,417
- 20
- 189
- 313