WCCI Performance Prediction Challenge

The challenge is over, but a new challenge is on-going using the same datasets, check it out!

linearSVC_Ensemble

Submitted by Reference

This method is one of the CLOP model examples. It uses an ensemble of linear SVC classifiers obtained with different hyperparameters.

Here is the model:
for k=1:3
base_model{k}=chain({standardize, svc(['shrinkage=' num2str(10^-(k-1))]) });
end
my_model=ensemble(base_model, 'signed_output=1');

For nova, no standardization is performed.

Dataset Balanced Error Test guess Guess error Test score Area Under Curve
Train Valid Test Train Valid Test
ada 0.2201 0.2187 0.2368 0.2201 0.0167 0.2535 0.8092 0.8055 0.7875
gina 0.1306 0.1277 0.1406 0.1306 0.01 0.1505 0.8693 0.8723 0.8595
hiva 0.2488 0.3971 0.3162 0.2488 0.0674 0.3836 0.7512 0.6029 0.6838
nova 0 0.112 0.0967 0 0.0967 0.1935 1 0.9073 0.9153
sylva 0.0859 0.0835 0.0847 0.0859 0.0012 0.0858 0.9141 0.9165 0.9153
Overall 0.1371 0.1878 0.175 0.1371 0.0384 0.2134 0.8688 0.8209 0.8323