Interview questions

Explain normalization, regularization, CTR, imbalance handling

Companies: Microsoft

CTR Prediction & Ads ML · Neural Networks & Training

Explain Overfitting and Transformer Basics

Companies: JPMorgan

Explain Overfitting and Underfitting in Machine Learning

Companies: Amazon

Explain overfitting vs underfitting and fixes

Companies: LinkedIn

ML Fundamentals · Model Evaluation

Explain overfitting, regularization, and LLM techniques

Companies: Amazon

AI Agents · ML Fundamentals

Explain overfitting, underfitting, and regularization

Companies: Pinterest

ML Fundamentals

Explain PCA and L2 Normalization in Machine Learning

Companies: Experian

Feature Engineering · ML Fundamentals

Explain precision/recall and compute NN output

Companies: Coinbase

ML Fundamentals · Model Evaluation

Explain Random Forest randomness and implications

Companies: Snapchat

Explain random forests, bagging, and evaluation

Companies: Amazon

Explain ranking cold-start strategies

Companies: Google

Recommendation Systems · Retrieval & Candidate Generation

Explain RF optimization and variable-importance pitfalls

Companies: Citadel

Explain RL policy types and modern policy gradients

Companies: TikTok

Explain RNN Applications Beyond Time-Series Forecasting

Companies: C3 Ai

Explain ROC-AUC vs PR-AUC tradeoffs

Companies: Databricks

Model Evaluation

Explain Sampled-Softmax Correction and Classification Loss Choice

Companies: ByteDance

Explain SFT, DPO, PPO, and the Role of KL Regularization

Companies: Siemens

Fine-Tuning & Alignment Techniques · Reinforcement Learning

Explain SHAP and build an ML project

Companies: Microsoft

ML System Design · Model Interpretability

Explain SHAP in an ML System

Companies: Microsoft

ML System Design · Model Interpretability

Explain SHAP vs VIF under collinearity

Companies: TikTok

Model Interpretability · Regression & Statistical Modeling

Explain SVM kernels and complexity

General practice