Dataford
Interview QuestionsInterview GuidesExperiencesMock InterviewsPricing
Get started

Accuracy as an Evaluation Metric

HardA/B Testing & Experimentation00:00
Practice interviewer
In session
5 left
00:00

Your question is Accuracy as an Evaluation Metric. Take a moment with it on the right.

Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).

You need to log in / sign up to chat or submit.

Problem

When should you use accuracy as an evaluation metric, and when should you not use it?

Asked in the Technical / Machine Learning Round stage. Discussion on model evaluation metrics.

Answer the question as a practical experimentation design exercise. Explain the assumptions required for accuracy to be meaningful, identify situations where it can be misleading, and propose an alternative metric strategy. Include a primary metric, guardrails, an explicit MDE, a sample-size calculation, unit-of-randomization choice, analysis plan, and a ship or do-not-ship rule.