Your question is Overfitting and Generalization Control. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You are training supervised learning models and notice that some candidates perform very well on training data but worse on unseen data. You want to explain what is happening and how to reduce it.
What is overfitting, and how can it be prevented?