> For the complete documentation index, see [llms.txt](https://julienbeaulieu.gitbook.io/wiki/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://julienbeaulieu.gitbook.io/wiki/sciences/machine-learning/support-vector-machines.md).

# Support Vector Machines

### The C Parameter

![](https://846345873-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LagOeJ2nL90MQERwhxy%2F-LjmGR4-Zkpsp-CXV3zt%2F-Ljvcq99yDEy-580RsVf%2Fimage.png?alt=media\&token=1b9fffa3-6589-4146-a476-d9d036e734f2)

![](https://846345873-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LagOeJ2nL90MQERwhxy%2F-LjmGR4-Zkpsp-CXV3zt%2F-Ljwir-KEtuK8w2ehoPc%2Fimage.png?alt=media\&token=566c3ca1-2df8-4d9c-b3a2-7c27ba7173aa)

If C is large, then we penalize classification errors more. We're focused on classification instead of finding a good margin, maybe because we're in the medical field and we do not wish to have an error in our classification. If C is very small, then it's mostly the margin error, we penalize the margin error and are focusing more on a large error than on classifying the points correctly.