SVM outputting the same prediction value for every input... Why is that?

Question

I use Encog and I use SVM for predict data. My training set values are not normalized but they are in [-1,1] range originally. I don't understand why the problem occurs.

My training data:

EURUSD_OPEN_CH,EURUSD_HIGH_CH,EURUSD_LOW_CH,EURUSD_CLOSE_CH,EURUSD_MACD,EURUSD_MACDS,EURUSD_STTDEV
 0.0134883819,0.0132838637,0.0135361889,0.0140344719,0.0023983892,0.0010403195,0.0054870487
 0.0001454143,0.0000969039,-0.0002216665,-0.0005261919,0.0035244907,0.0013168603,0.0070012526
 -0.0005261846,0.0006574986,0.0001593581,0.0009628839,0.0044774819,0.0017225556,0.0081131621
 0.0009282350,-0.0001867452,-0.0004156506,-0.0005882475,0.0051052958,0.0021969854,0.0088044648
 -0.0005605769,-0.0006641071,0.0001455382,0.0000069246,0.0055397905,0.0027231400,0.0092672117
 (...)

Should I normalize these values? I think this can't be a problem, but who knows... I train the SVM and everything seems right, but when I evaluate the SVM, the output is the same for every input. I can attach code if it's neccessary.

Answer 1

I'm such a noob... Normalization solved the problem. These values were too small to predict, so I normalized the whole CSV to [0.1,0.9] range, and it helped.