ML Theory

Interview

Explain the bias-variance tradeoff. How do you diagnose which is hurting your model?

Tests whether you understand fundamental model behavior beyond memorized definitions, and whether you can diagnose real-world problems.

Interview

Why do we use cross-entropy loss for classification instead of MSE?

Tests whether you understand the math behind the choice, not just which loss to import.

Interview

You're building a fraud detection model where 0.1% of transactions are fraud. Why is accuracy a bad metric and what should you use?

Tests practical evaluation knowledge — the imbalanced-class case is where most metric mistakes happen.

Interview

When does classical ML with feature engineering beat deep learning?

Modern interviewers want signal that you don't reach for deep learning by default.

Interview

Walk me through how Adam works, and when you'd use it vs SGD with momentum.

Tests deeper optimizer knowledge — separates 'studied for the interview' from 'has shipped models'.

Interview

Your model has 95% training accuracy but 60% test accuracy. What do you investigate?

Classic diagnostic question. Tests whether you have a structured debugging process, not just memorized fixes.

Interview

What's the difference between L1 and L2 regularization, and when would you use each?

Quick check on fundamental ML knowledge — and whether you can connect math to practical model behavior.

Interview

How do you split data for a time-series model? Why not just random split?

Quick filter for whether you've worked with temporal data — this is the single most common ML mistake.

Prompt

ML Concept Deep-Dive (Interview Style)

Have a model walk through a complex ML/AI concept the way you'd explain it in an interview.