Subset Selection Least Squares Interpretability Generalized Additive Models Trees Bagging, Boosting Support Vector Machines Low High Flexibility In a certain regression problem, the number of predictors is extremely large, and the number of observations is small. Do you think Lasso or Support Vector Machines (SVM) would perform better? Unable to determine SVM is better because it can handle small n very well Lasso is better because it is highly interpretable. Lasso is better because it is less flexible and won't overfit the dataset with small n. SVM is better because it is flexible and can fit the large number of predictors