LibSVM classification results differ between Weka and Rapidminer

Msin

Hi,

Using Weka and Rapidminer, I got different classification results on the same dataset with LibSVM. Even when I made the same parameters that I could change on RapidMiner in both programs, Weka gave 75% and Rapidminer 55% classification accuracy.

Also, RapidMiner SVM and Weka SMO results differ greatly too.

I would be very grateful if you could explain the reasons for these two problems.

Thanks.

MartinLiebig

Well, its kind of expected. Slight differences in implementation choices can make a big impact.

But also make sure that you set all random seeds to the same values to make fair comparisons.

BR,

Martin