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.

1635
questions
16
categories
50
companies

Showing 20 of 746 questions

MediumMachine LearningЯндекс

What does logistic regression architecture look like?

logistic-regressionarchitecturelinear-models
Practice in bot
MediumMachine LearningЯндекс

How is logistic regression trained?

logistic-regressiontrainingoptimization
Practice in bot
MediumMachine LearningЯндекс

Can logistic regression get stuck in local minimum?

logistic-regressionoptimizationconvexity
Practice in bot
EasyMachine LearningЯндекс

How to understand if model is overfitted?

overfittingvalidationmodel-evaluation
Practice in bot
MediumMachine LearningЯндекс

What regularization methods exist?

regularizationoverfittingmethods
Practice in bot
EasyMachine LearningЯндекс

What metrics can be used for binary classification?

binary-classificationmetricsevaluation
Practice in bot
MediumMachine LearningЯндекс

What is plotted on X and Y axes in ROC curve?

roc-curveaxestpr-fpr
Practice in bot
HardMachine LearningЯндекс

How will ROC-AUC change if all probabilities are divided in half?

roc-aucprobability-transformationinvariance
Practice in bot
MediumMachine LearningЯндекс

Can we deploy model to production based on ROC-AUC 0.81 vs 0.80?

model-deploymentstatistical-significancepractical-significance
Practice in bot
MediumMachine LearningЯндекс

How to study model quality in more detail?

model-analysisdetailed-evaluationdiagnostics
Practice in bot
MediumMachine LearningЯндекс

What model quality metrics do you know?

metricsmodel-qualityevaluation
Practice in bot
MediumMachine Learning

What baseline can you suggest building?

baselinemodel-developmentstarting-point
Practice in bot
EasyMachine LearningСбер

Why is baseline needed in ML model development?

baselinemodel-developmentbest-practices
Practice in bot
MediumMachine LearningСбер

What is MAPE and how is it calculated?

maperegression-metricspercentage-error
Practice in bot
MediumMachine LearningМосбиржа

What methods can be used for training on imbalanced data?

imbalanced-datasamplingcost-sensitive
Practice in bot
MediumMachine LearningМосбиржа

What to do with highly correlated features?

correlationmulticollinearityfeature-engineering
Practice in bot
MediumMachine LearningМосбиржа

Why do linear models perform poorly with imbalanced data?

imbalanced-datalinear-modelsclassification
Practice in bot
MediumMachine LearningМосбиржа

What is the fundamental difference between SVM and logistic regression?

svmlogistic-regressionclassification
Practice in bot
MediumMachine LearningМосбиржа

What do you know about ensemble methods?

ensemblebaggingboostingstacking
Practice in bot
HardMachine LearningМосбиржа

How do CatBoost, LightGBM, XGBoost differ in tree construction?

catboostlightgbmxgboosttree-construction
Practice in bot

Prepare for your next interview with Vibe Interview.

Download Vibe Interview
Machine Learning interview questions — page 23 | Vibe Interview