A garden-watering model was retuned. Agreed ML functional-performance metrics exist. What should A/B testing check before the update replaces the previous variant?
Select an answer to reveal the explanation.
Short Explanation
Before a retuned garden-watering model replaces the previous variant, A/B testing checks that the update performs as well as, or better than, the previous variant on the agreed ML functional-performance metrics. Shipping a worse retune, swapping in back-to-back defect hunting, or treating a Chapter 5 type constraint as the only metric miss that check.
Full Explanation
A/B testing of model updates checks that the new variant is as good as, or better than, the previous one against agreed ML functional-performance criteria. Shipping a worse retune, swapping in back-to-back defect hunting, or substituting a Chapter 5 constraint miss that check.