WCCI Performance Prediction Challenge

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

CLOP-models-only-1

Submitted by Juha Reunanen

Only CLOP models used.
Validation labels utilized for hiva, but not for the other datasets. (No particular reason for that; just got the computations for the others finished before February, and didn't redo them yet.)

Dataset Balanced Error Test guess Guess error Test score Area Under Curve
Train Valid Test Train Valid Test
ada 0.0829 0.2406 0.2494 0.2173 0.0322 0.2816 0.9864 0.8672 0.8532
gina 0.0756 0.0735 0.0976 0.0932 0.0044 0.1016 0.9748 0.9606 0.9578
hiva 0.0148 0.0357 0.3678 0.3235 0.0443 0.412 1 1 0.7118
nova 0.012 0.054 0.0697 0.0843 0.0146 0.0842 0.9995 0.9658 0.9752
sylva 0.01 0.0404 0.0327 0.0312 0.0015 0.0337 0.9989 0.9989 0.9944
Overall 0.0391 0.0888 0.1634 0.1499 0.0194 0.1826 0.9919 0.9585 0.8985

This entry is a complete valid challenge entry.