Supervised Learning - Classification Week 7 Challenge

1) Advantages:

a) Support vector machine works comparably well when there is an understandable margin of dissociation between classes.

b) It is more productive in high-dimensional spaces.

c) It works well with unstructured data like text, images and trees.

d) Svm are generalized models taking some bias into consideration therefore there is a lower chance of overfitting.

e) Well suited for complex small and medium datasets.

f) has various kernel functions that can capture complex decision problems.

Disadvantages:

a)Sensitive to noisy or mislabeled data.

b) stuggles with imbalanced datasets.

c) Reqiures careful hyperparameter tuning.

d) Computaionally intensive training.

e)It is hard to interpret the model. There is also a lack of transparency in parameters.