Your question is Choosing Features for Predictive Models. 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're training a supervised learning model and have many possible inputs, including raw fields, derived variables, and historical aggregates. You want a principled way to decide which features belong in the model.
How would you choose features for a predictive model?