Objective 3.4 Evaluate the Model AIP-210 Practice Questions (Page 8)

Questions 36–37

1. 36expert · hard

   A data scientist is evaluating a binary classifier on a highly imbalanced dataset where 99% of samples are negative. The model predicts all samples as negative. Which metric would be most misleading to report?

   • APrecision
   • BF1-score
   • CRecall
   • DAccuracy
   Reveal Solution Discussion Select an answer first
2. 37application · medium

   A data scientist is training a neural network. The training loss decreases steadily, but the validation loss starts to increase after 10 epochs. What is the best course of action?

   • AStop training early and use the model from the epoch with the lowest validation loss
   • BContinue training for more epochs to see if validation loss decreases again
   • CAdd more layers to the network to increase capacity
   • DIncrease the learning rate to escape local minima
   Reveal Solution Discussion Select an answer first