In SAS Viya's gradient boosting implementation, a data scientist wants to prevent individual trees from memorizing specific training observations. Which combination of parameters directly implements this goal?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because stochastic gradient boosting — using SUBSAMPLERATE (row subsampling) and COLSAMPLEBYTREE (column subsampling) less than 1.0 — ensures that each individual tree is trained on a random subset of observations and variables. This randomness prevents any single tree from seeing all training observations and memorizing their noise, while also increasing diversity across trees in the ensemble.
Full explanation below image
Full Explanation
B is correct because stochastic gradient boosting — using SUBSAMPLERATE (row subsampling) and COLSAMPLEBYTREE (column subsampling) less than 1.0 — ensures that each individual tree is trained on a random subset of observations and variables. This randomness prevents any single tree from seeing all training observations and memorizing their noise, while also increasing diversity across trees in the ensemble. A slows learning but does not add tree-level stochasticity. C (deeper trees) increases the chance of memorizing observations. D (learning rate=1.0) is no shrinkage and leads to aggressive overfitting.