In this section, we will look at the other major concept of supervised ML, which is called classification techniques. This is also called statistical classification.
Statistical classification is used to identify a category for a given new observation. So, we have many categories in which we can put the new observation. However, we are not going to blindly choose any category, but we will use the given dataset, and based on this dataset, we will try to identify the best suited category for the new observation and put our observation in this category or class.
Let's take an example from the NLP domain itself. You have a dataset that contains a bunch of emails and those emails already have a class label, which is either spam ...
