Support vector machines

 

It is now time to move on to support vector machines, to see if they help us better define the profile of those customers more inclined to get into default status.

First of all, you should notice that support vector machines are way more recent models since they where developed around the 1990s. Secondly, you should notice that when we talk about SVMs, we are actually talking about a family of models rather than a single one.

I am going to show you now just what you need to know to understand the main concepts behind this model, but I will point out to you some good references in case you want to deepen your knowledge of the topic.

The intuition behind support vector machines

There are three main concepts you have to bear in mind when talking about support vector machines:

• The hyperplane
• The maximal margin classifier
• The support vector

The hyperplane

The hyperplane can be considered as the first brick to be employed when building a support vector machine.

Have you ever played...