hard20 pts · first answer countsdata-leakagefeature-engineering
A feature that is too good
Your churn model reaches 0.99 AUC. The most important feature is "days_since_last_support_ticket_closed", and many churned users have a final ticket titled "cancel account". What is the most likely issue?
Discussion 0
Join free to post in the discussion.
Related questions
- Which model needs feature scalingMachine Learning Engineer
- Encoding a city featureMachine Learning Engineer
- Scaling before splittingMachine Learning Engineer
- Millions of product IDs as a featureMachine Learning Engineer
- Target encoding without leakageMachine Learning Engineer
- Several scans per patientMachine Learning Engineer
- SMOTE applied before cross-validationMachine Learning Engineer
- Encoding a city columnData Scientist