Nontrivial use case 2: use of Shapely values for feature selection and feature engineering
Is there an easy way to force interactions at the very first splits of XGBoost trees? It might help when applying particular business rules in some real world problems
Hi Bojan, you might also like to author a blog about FIGS (Fast Interpretable Greedy-Tree Sums) , from Berkeley, they have an interesting approach
Is there an easy way to force interactions at the very first splits of XGBoost trees? It might help when applying particular business rules in some real world problems
Hi Bojan, you might also like to author a blog about FIGS (Fast Interpretable Greedy-Tree Sums) , from Berkeley, they have an interesting approach