Question Bank
Machine Learning interview questions Naming a model or a metric is only the start of an interview answer. Explain why it fits the task, and connect training, regularization, validation and evaluation to a concrete example. Start with your own explanation, then state its assumptions and limitations.
Medium Machine Learning Яндекс
What does logistic regression architecture look like?
logistic-regression architecture linear-models
Practice in bot Medium Machine Learning Яндекс
How is logistic regression trained?
logistic-regression training optimization
Practice in bot Medium Machine Learning Яндекс
Can logistic regression get stuck in local minimum?
logistic-regression optimization convexity
Practice in bot Easy Machine Learning Яндекс
How to understand if model is overfitted?
overfitting validation model-evaluation
Practice in bot Medium Machine Learning Яндекс
What regularization methods exist?
regularization overfitting methods
Practice in bot Easy Machine Learning Яндекс
What metrics can be used for binary classification?
binary-classification metrics evaluation
Practice in bot Medium Machine Learning Яндекс
What is plotted on X and Y axes in ROC curve?
roc-curve axes tpr-fpr
Practice in bot Hard Machine Learning Яндекс
How will ROC-AUC change if all probabilities are divided in half?
roc-auc probability-transformation invariance
Practice in bot Medium Machine Learning Яндекс
Can we deploy model to production based on ROC-AUC 0.81 vs 0.80?
model-deployment statistical-significance practical-significance
Practice in bot Medium Machine Learning Яндекс
How to study model quality in more detail?
model-analysis detailed-evaluation diagnostics
Practice in bot Medium Machine Learning Яндекс
What model quality metrics do you know?
metrics model-quality evaluation
Practice in bot Medium Machine Learning
What baseline can you suggest building?
baseline model-development starting-point
Practice in bot Easy Machine Learning Сбер
Why is baseline needed in ML model development?
baseline model-development best-practices
Practice in bot Medium Machine Learning Сбер
What is MAPE and how is it calculated?
mape regression-metrics percentage-error
Practice in bot Medium Machine Learning Мосбиржа
What methods can be used for training on imbalanced data?
imbalanced-data sampling cost-sensitive
Practice in bot Medium Machine Learning Мосбиржа
What to do with highly correlated features?
correlation multicollinearity feature-engineering
Practice in bot Medium Machine Learning Мосбиржа
Why do linear models perform poorly with imbalanced data?
imbalanced-data linear-models classification
Practice in bot Medium Machine Learning Мосбиржа
What is the fundamental difference between SVM and logistic regression?
svm logistic-regression classification
Practice in bot Medium Machine Learning Мосбиржа
What do you know about ensemble methods?
ensemble bagging boosting stacking
Practice in bot Hard Machine Learning Мосбиржа
How do CatBoost, LightGBM, XGBoost differ in tree construction?
catboost lightgbm xgboost tree-construction
Practice in bot Prepare for your next interview with Vibe Interview.
Download Vibe Interview