Name three situations where you should NOT reach for machine learning.
mediumAnswer
- (1) A hand-crafted rule solves it deterministically — 'if age < 18, deny' beats a model both in accuracy and interpretability.
- (2) No representative labeled data (or feasible way to get any) — you'll just fit noise.
- (3) The prediction has to be perfectly explainable / auditable and even a linear model is too opaque (e.g., certain regulatory decisions).
- Also: when the cost of a wrong prediction is catastrophic and the marginal accuracy gain is tiny — deterministic rules or human-in-the-loop win.
Check yourself — multiple choice
- Always use ML
- Deterministic rule suffices, no representative labels, or extreme explainability / cost-of-error requirements
- Only refuse ML on time-series
- ML is only for computer vision
Rules-first, label-availability, and explainability/cost-of-error should be checked before choosing ML.
#interview-scenarios
Practise Supervised Learning
215 interview questions in this topic.
Related questions
- You must pick ONE metric for your model. How do you decide?
- Your new model has 60% AUC and the baseline had 75%. How do you debug?
- You detect concept drift in production. What do you do?
- How do you train and evaluate a model when labels arrive weeks after predictions?
- Your model has great offline metrics. What do you check before serving it in production?
- An interviewer asks you to build a churn model. What do you do before touching any algorithm?