Professional Machine Learning Engineer

Question

You are developing a model to detect fraudulent credit card transactions. You need to prioritize detection because missing even one fraudulent transaction could severely affect the credit card holder.

You used AutoML to train a model on users' profile information and credit card transaction data. After training the initial model, you notice that it fails to detect many fraudulent transactions. How should you adjust the training parameters in AutoML to improve model performance?

Choose two

Explanation

Fraud detection should prioritize recall because false negatives allow fraudulent transactions to go undetected. Decreasing the score threshold labels more transactions as fraud, which reduces false negatives. Adding more positive fraud examples also improves the model's ability to learn and recognize the fraud class, particularly when that class is underrepresented.

Professional Machine Learning Engineer

AstroTutor

Notes

Readiness

QuestionQ52

Community Discussion