Should I use Deep Learning?

Patricia works for a bank and wants to help her company make smarter loans. She'd like to predict the probability of a borrower defaulting on a loan based on information in their application, such as their credit history, education level, income, and assets. Patricia would then use this amount to determine the interest rate of the loan.

Patricia has hundreds of thousands of examples of loans from the past ten years.

Patricia runs her idea past the legal department, and they remind her that there are laws about how interest rates can be determined that protect borrowers from discrimination on the basis of age, gender, race, and other factors.

Based on this information, should Patricia use Deep Learning or Explainable AI for this problem?

Answer the question

50 XP

Possible Answers

Explainable AI, because she doesn't have enough data for Deep Learning.
press1
Explainable AI, because she needs to be able to justify how each interest rate was calculated.
press2
Deep Learning, because the results need to be as accurate as possible.
press3
Deep Learning, because the data will have many features, and Explainable AI can only handle a few.
press4