A machine learning model is used to predict whether magazine subscribers will cancel their annual subscription. The data shows a significant class imbalance: 90% renewal, 10% cancellation.
The model achieves 99% accuracy in predicting cancellations and 82% accuracy in predicting renewals.
The question assesses the interpretation of these results. Option A incorrectly suggests that renewal accuracy should be higher than cancellation accuracy. Option B incorrectly compares the model's performance to a naive baseline of always predicting renewal. Option D incorrectly focuses solely on the overall accuracy being above 80%. Option C is correct, highlighting the difficulty in accurately predicting the minority class (cancellations) due to the limited data available for that group.
The correct answer is C.
You work for a magazine publisher and have been tasked with predicting whether customers will cancel their annual subscription. In your exploratory data analysis, you find that 90% of individuals renew their subscription every year, and only 10% of individuals cancel their subscription. After training a NN Classifier, your model predicts those who cancel their subscription with 99% accuracy and predicts those who renew their subscription with 82% accuracy. How should you interpret these results?
Skip the extension — just come straight here.
We’ve built a fast, permanent tool you can bookmark and use anytime.
Go To Paywall Unblock Tool