Why the sign of predicted labels and decision values are sometimes reversed?
Nothing is wrong. Very likely you have two labels +1/-1 and the first instance in your data has -1. Think about the case of labels +5/+10. Since SVM needs to use +1/-1, internally we map +5/+10 to +1/-1 according to which label appears first. Hence a positive decision value implies that we should predict the “internal” +1, which may not be the +1 in the input file.
Related Questions
- Do you think that major labels will be decimated by the Internet, as some have predicted, or will they simply adapt to the technology, remain dominant and change the way they work?
- Why the sign of predicted labels and decision values are sometimes reversed?
- What are p values and how are p values used in clinical decision making?
