MLS-C01 · Question #36
A large mobile network operating company is building a machine learning model to predict customers who are likely to unsubscribe from the service. The company plans to offer an incentive for these…
The correct answer is C. The model is 86% accurate and the cost incurred by the company as a result of false positives is. The key business context is: cost of churn >> cost of incentive. A false positive means the model predicts a customer will churn but they would not have - the company offers an incentive unnecessarily. This is the cheaper mistake. A false negative means the model predicts a…
Question
A large mobile network operating company is building a machine learning model to predict customers who are likely to unsubscribe from the service. The company plans to offer an incentive for these customers as the cost of churn is far greater than the cost of the incentive. The model produces the following confusion matrix after evaluating on a test dataset of 100 customers:
Based on the model evaluation results, why is this a viable model for production?
Exhibit
Options
- AThe model is 86% accurate and the cost incurred by the company as a result of false negatives is
- BThe precision of the model is 86%, which is less than the accuracy of the model.
- CThe model is 86% accurate and the cost incurred by the company as a result of false positives is
- DThe precision of the model is 86%, which is greater than the accuracy of the model.
How the community answered
(54 responses)- A13% (7)
- B6% (3)
- C63% (34)
- D19% (10)
Explanation
The key business context is: cost of churn >> cost of incentive. A false positive means the model predicts a customer will churn but they would not have - the company offers an incentive unnecessarily. This is the cheaper mistake. A false negative means the model predicts a customer will NOT churn but they do - the company loses that customer entirely, the far more expensive outcome. Answer C correctly identifies that the model is 86% accurate and that the cost of false positives (giving incentives to loyal customers) is acceptable because it is much lower than the cost of false negatives (missing actual churners). The model's value comes from catching most true churners, even at the expense of some wasted incentives.
Topics
Community Discussion
No community discussion yet for this question.