WCCI Performance Prediction Challenge

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

GbO+MVf+SVM5

Submitted by Vladimir Nikulin

see for details my paper
"Learning with Mean-Variance Filtering, SVM and Gradient-based Optimization", 8 pages
(submitted to WCCI in January 2006).

Dataset Balanced Error Test guess Guess error Test score Area Under Curve
Train Valid Test Train Valid Test
ada 0.1632 0.1576 0.1873 0.166 0.0213 0.2086 0.8366 0.8612 0.804
gina 0 0 0.0573 0.06 0.0027 0.0597 1 1 0.9348
hiva 0.2077 0.2118 0.3516 0.23 0.1216 0.4733 0.768 0.784 0.641
nova 0 0.004 0.0591 0.03 0.0291 0.0881 1 0.9954 0.9125
sylva 0.0094 0.0065 0.0122 0.01 0.0022 0.0143 0.9977 0.9987 0.9913
Overall 0.0761 0.076 0.1335 0.0992 0.0354 0.1688 0.9205 0.9279 0.8567

This entry is a complete valid challenge entry.