Welcome to your interview.
The question is on your right: Handling Imbalanced Fraud Labels. Take a moment with it first.
Talk your thinking through with me if you like - when you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes). Discussion and graded submissions share your five interviewer interactions, so spend them well.
You are training a binary classifier where the positive class is rare, as is common in fraud detection. A model with high accuracy can still be useless if it misses most true positives or floods investigators with false alarms.
How do you handle highly imbalanced datasets, which are common in insurance fraud detection?