The Support Vector Machine Classifier (SVC) does not support multiclass classification natively. But, we can use a One-Vs-One (OVO) or One-Vs-Rest (OVR) strategy with SVC to solve a multiclass classification problem. As we know, in a binary classification problem, the target variable can take two different values. And in a multiclass classification problem, the target variable can take more than two different values.

Let’s say the target variable of a multiclass classification problem can take three different values A, B, and C. In that case, if we use a One-Vs-Rest (OVR) strategy, then the multiclass classification problem is broken into the following binary classification problems:

Problem 1: A vs. (B, C)
Problem 2: B vs. (A, C)
Problem 3: C vs. (A, B)

So, if the target variable can take n possible values, then the multiclass classification problem is broken into n number of binary classification problems.

On the other hand, if we use the One-Vs-One (OVO) strategy, then the same problem will be broken into the following binary classification problems:

Problem 1: A vs. B
Problem 2: A vs. C
Problem 3: B vs. C

So, if the target variable can take n possible values, then the multiclass classification problem is broken into n(n-1)/2 number of binary classification problems.

Now, the binary classification problems can be solved using a binary classifier like the SVC, and the results can be used to predict the outcome of the target variable.

So, if we want to use the SVC for solving a multiclass classification problem, we can do so in the following way: …