Suppose you are building a SVM model on data X. The data X can be error prone which means that you should not trust any specific data point too much. Now think that you want to build a SVM model which has quadratic kernel function of polynomial degree 2 that uses Slack variable C as one of it’s hyper parameter.What would happen when you use very small C (C~0)?

The correct answer is: A. Misclassification would happen.

When you use a very small value for C, the SVM model will try to classify all data points as correctly as possible, even if some of the data points are error prone. This can lead to misclassification, as the model will be more likely to classify data points incorrectly in order to avoid violating the constraints.

Here is a more detailed explanation of each option:

• Option A: Misclassification would happen. This is the correct answer, as explained above.
• Option B: Data will be correctly classified. This is not necessarily the case. As explained above, when you use a very small value for C, the SVM model will try to classify all data points as correctly as possible, even if some of the data points are error prone. This can lead to misclassification, as the model will be more likely to classify data points incorrectly in order to avoid violating the constraints.
• Option C: Can’t say. This is not a correct answer, as it is possible to say what would happen when you use a very small value for C. As explained above, when you use a very small value for C, the SVM model will try to classify all data points as correctly as possible, even if some of the data points are error prone. This can lead to misclassification, as the model will be more likely to classify data points incorrectly in order to avoid violating the constraints.
• Option D: None of these. This is not a correct answer, as one of the options is correct.