Table 14 Results: Prediction accuracy with SVM and CART
From: An alternative approach to dimension reduction for pareto distributed data: a case study
Model | AUC-ROC Ten-fold cross validation | Standard Deviation | AUC-ROC testing |
|---|---|---|---|
SVM w/ categorical | 69% | 10.4% | 80% |
SVM w/o Categorical | 76% | 2.6% | 77% |
CART w/ Categorical | 65% | 6.3% | 73% |
CART w/o Categorical | 74% | 2.7% | 74% |