You are a manager in customer service department in Amazon. Daily, your team 100,000 customer emails. You need to develop a model, that scans those emails into two general category: complains and approvals Complaints must be sent to a specific department to take care of them, either by refunding the customer or giving them some promotions Approvals need to be sent to another department, to try to encourage happy customers more to purchase more using a variety of techniques Approval is labelled as positive and complaints is labelled as negative Surely, you understand the importance of reading those emails by a machine and classifyin them into the correct category. Your model is not perfect though For every TN, in average, we make $10, for every TP we make, $8, and for every FP we will lose $3 and for every Fn we will lose $12. For your model, TN=20, TP=90, FN=15, FP=2. All numbers are in millions. For building the model, 127 observations has been used where 110 of them were positive A) Which performance metrics will you use for this model? The accepted answeres are "accuracy", "precision", "recall", and "f1_score". B) Considering the role of imbalanced data, what is the expected value of this model. The answer to this question is a number. C) Per each email, you are paying $0.1 to your data scientist to do the predction. Based on EV you have, shall you fire him/her or promote him/her? Explain why.