Welcome to your interview.
The question is on your right: XGBoost vs Deep Learning Tabular. 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're comparing candidate models for a supervised learning problem on tabular behavioral data. You want to understand when a tree ensemble is the better choice and when a deep learning model is worth the added complexity.
How do tree-based ensemble methods like XGBoost compare to deep learning models for tabular behavioral data?