MLS-C01 Question 121
Single answerYou are building a machine learning model to predict customer churn for an e-commerce platform. After training the model, you notice that it has a high accuracy but performs poorly in identifying customers who are likely to churn. Which metric should you prioritize to assess and improve the model's performance in this scenario?
- A
Precision
- B
Recall
- C
F1 Score
- D
Mean Squared Error (MSE)
Show answer and explanation
Correct answer: B
Explanation
In a customer churn prediction problem, the primary goal is to identify all customers who are likely to churn, even if this means tolerating some false positives. Recall is the most appropriate metric for this, as it ensures that the model captures as many true positives as possible, minimizing false negatives. While other metrics like precision or F1 Score are useful in specific contexts, recall directly aligns with the business objective of reducing customer churn.
- A. Incorrect.
Precision measures the proportion of correctly identified positive cases out of all predicted positive cases. While useful in some cases, it is not the best metric for identifying churners, as it doesn't focus on capturing all true positives.
- B. Correct.
Recall measures the proportion of correctly identified positive cases out of all actual positive cases. In this scenario, where identifying all churners is critical, recall should be prioritized to minimize false negatives.
- C. Incorrect.
F1 Score is the harmonic mean of precision and recall. While it balances the two, focusing on recall alone is more appropriate here because the business impact of missing churners (false negatives) is higher than the cost of false positives.
- D. Incorrect.
Mean Squared Error (MSE) is a regression metric and is not applicable to this classification problem. It cannot help assess the ability of the model to identify churners.