# Different accuracy for different rng values

While tuning the SVM classification model in Matlab, I came across the rng function in matlab in which seed (stabilizes the random shuffling of the data in the algorithm) is changed. When the function called is rng(1) then I am getting one accuracy value (99%). When it is changed to rng(2) then I am getting another value (57%). So there is a huge change in accuracy as visible. What does this mean? Am I training it wrong?

The train and test set correct rate (in %) that I am getting with different runs without changing rng are(train,test)
(96, 82.8)
(94.6, 95.3)
(96, 85.9)
(96, 90)
(95, 95)

• What are the testing errors of both? Nothing can be said by just looking at the training errors. Maybe rng(1) is better than rng(2) or maybe it is overfitting.
– Dawny33
Aug 9 '16 at 5:48
• @Dawny33 So does this mean that there is overfitting? A good model should have the same accuracy for any rng right? Aug 9 '16 at 5:52

The training errors in this dataset has a huge difference (99% vs 57%). So, maybe the one with the rng(1) split has overfitted your dataset.

So there is a huge change in accuracy as visible. What does this mean? Am I training it wrong?

The huge change might be due to overfitting. (Also, judge the model through validation curves, and then fit a model which balances the bias-variance plot.)

• made a small change in the question. Let me know whether still there is over-fitting or not Aug 9 '16 at 7:15
• @Rishika No, I don't think there's any overfitting there. But, that's without changing the rng value, right?
– Dawny33
Aug 9 '16 at 7:17
• yes. This is without changing rng Aug 9 '16 at 7:22
• @Rishika The model looks good to me, then :)
– Dawny33
Aug 9 '16 at 7:25