Hi Ady. Are you selecting parameters separately for the two models in the separate case? Btw, if you are modelling a single normal, maybe EllipticEnvelope would work better.
Best, Andy On 08/04/2015 01:07 PM, Ady Wahyudi Paundu wrote: > Hi all, > > How am I supposed to work with multiple set of normal data for one-class SVM? > If I have two normal scenario data set, A and B for learning phase, > should I create predictor model separately (M(A) + M(B)) or can I > combine A and B to create just a single predictor model (M(A+B))? > > I have try both approach using one-class SVM in scikit-learn, and my > results shows that FPR for combined normal data set is significantly > higher (more than 30% in average) than separate prediction (suggesting > that separate prediction is better than combined prediction). I just > want to confirmed this findings, is that how it supposed to be? > > Are there any way to improved combined prediction model for one-class SVM? > > Thank you in advance. > > Best regards, > Ady > > ------------------------------------------------------------------------------ > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general ------------------------------------------------------------------------------ _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
