Explain normalization, regularization, CTR, imbalance handling

Q: Explain normalization, regularization, CTR, imbalance handling

This is a Machine Learning interview question from Microsoft for Software Engineer roles. View the full question and solution on PracHub.

Q: How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

Question

Loading...

You are interviewing for an applied ML role. Answer the following fundamentals clearly and concretely (you may use equations and practical examples):

Layer Normalization vs. Batch Normalization

What are the key differences in how they compute statistics?
How do they behave during training vs. inference?
When would you prefer one over the other (e.g., CV vs. NLP/LLMs, small batch sizes, RNNs/Transformers)?

Regularization terms/techniques

Compare common regularization approaches such as L2 / weight decay , L1 , dropout , early stopping , and data augmentation .
What model behaviors do they encourage, and what are typical pitfalls?

CTR (Click-Through Rate) prediction

Outline a practical approach to CTR prediction: data/feature setup (categorical + continuous), model families (e.g., logistic regression, factorization machines, deep models), training objective, and evaluation.
Mention online concerns such as calibration and serving constraints.

Handling imbalanced data

Describe strategies to train and evaluate models when positives are rare.
Include both data-level and algorithm-level techniques, and appropriate metrics.

Explain normalization, regularization, CTR, imbalance handling

Solution

Comments (0)