|
The table compares the performance of a decision tree derived using the C4.5 algorithm and a Random Forest, both generated with standard parameters. Ten-fold stratified cross-validation (on MTS) and validation on an independent protectivity validation set (MVS) are compared |
||||||
| C4.5 |
Random Forest |
|||||
|
|
||||||
| % sep |
FPrate |
TPrate |
% sep |
FPrate |
TPrate |
|
|
|
||||||
| Cross-validation |
70.41 |
0.24 |
0.65 |
83.39 |
0.15 |
0.82 |
| Validation-set |
73.64 |
0.26 |
0.73 |
84.27 |
0.15 |
0.83 |
|
Column abbreviations: %sep (% class separation), FPrate (False Positive rate) and TPrate (True Positive rate). | ||||||
Sollner et al. Immunome Research 2008 4:1 doi:10.1186/1745-7580-4-1 |
||||||