ML model risks · Question 41 of 60
After a model update, a team reports: the new model crashes immediately after deployment, and in another version previously correct cases no longer work. Which mitigations fit these two risks?
2 answers are correct. Hard
Show answer
Answer
- A Smoke testing against immediate failure after deployment
- B Regression testing against regression after deployment
Explanation
Smoke testing helps against the risk that deploying an updated model causes immediate failure, and regression testing against a regression caused by the deployment. Drift testing targets data and concept drift in operation.