Fraud detection problem

The fraud detection problem is not a supervised learning problem. We have an unbalanced class situation in our fraud detection scenario. What do we have to say abouttheimportance of the F1 scorein relation to the target variable? First, the target variable is a binary label. The F1 score is relevant to our fraud detection problem because we have an unbalanced class, where one class is practically more important than the other. What do we mean by that?The bottom line of the fraud detection classification process concerns whether a certain instance is fraudulent, and getting the classifier to classify or label this instance correctly as fraudulent.The emphasis is not on labeling an instance as non-fraudulent.

 To reiterate, there are two classes in our fraud detection problem:

• Fraudulent 
• Non-fraudulent

That said, we will now look at the dataset that this implementation depends upon 

Fraud detection dataset at a glance

Download the dataset from the ModernScalaProjects_Code...