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

HardMachine LearningМосбиржа

Which ROC-AUC variation is better: 0.1, 0.7, or 0.85?

roc-aucmetricsevaluation
Practice in bot
HardMachine LearningМосбиржа

For heavily imbalanced classes, which to choose: ROC-AUC or PR-AUC?

imbalanced-datametricspr-aucroc-auc
Practice in bot
MediumMachine LearningLamoda

We have regression task, target from 0 to 100. What will be the output distribution for each algorithm?

regressionoutput-distributionalgorithms
Practice in bot
MediumMachine LearningLamoda

What categorical variable encoding methods exist? Pros and cons?

categorical-encodingone-hottarget-encoding
Practice in bot
MediumMachine LearningLamoda

What are the disadvantages of target encoding?

target-encodingdata-leakageoverfitting
Practice in bot
HardMachine LearningLamoda

How does target encoding work in CatBoost?

catboosttarget-encodingordered-statistics
Practice in bot
MediumMachine LearningLamoda

How to build a tree in general, what criteria to use?

decision-treestree-constructioninformation-gain
Practice in bot
MediumMachine LearningLamoda

What are the advantages and disadvantages of trees?

decision-treesinterpretabilityoverfitting
Practice in bot
HardMachine LearningLamoda

In terms of bias-variance, how does a tree behave?

decision-treesbias-varianceoverfitting
Practice in bot
MediumMachine LearningLamoda

What kind of trees are built in boosting and random forest?

random-forestgradient-boostingensemble
Practice in bot
MediumMachine LearningLamoda

Best practice for boosting tuning - what to tune first?

hyperparameter-tuninggradient-boostingoptimization
Practice in bot
MediumMachine LearningLamoda

What happens to variance in random forest?

random-forestvariance-reductionensemble
Practice in bot
HardMachine LearningLamoda

Why does model variance plateau with increasing complexity?

bias-variancemodel-complexityoverfitting
Practice in bot
MediumMachine LearningLamoda

How is gradient used in gradient boosting?

gradient-boostingoptimizationloss-function
Practice in bot
HardMachine LearningLamoda

What does the next tree learn in boosting?

boostinggradient-descentresiduals
Practice in bot
MediumMachine LearningLamoda

How to evaluate feature importance - feature importance vs SHAP?

feature-importanceshapinterpretability
Practice in bot
MediumMachine Learning

Why doesn't boosting extrapolate beyond training data?

gradient-boostingextrapolationdecision-trees
Practice in bot
MediumMachine Learning

What do you understand by hyperparameter optimization?

hyperparameter-optimizationgrid-searchbayesian-optimization
Practice in bot
MediumMachine Learning

How to prevent data leakage in medical data?

data-leakagemedical-datatemporal-splitting
Practice in bot
MediumMachine Learning

What is model governance and why is it important in production?

model-governancemlopscompliance
Practice in bot

Prepare for your next interview with Vibe Interview.

Download Vibe Interview
Machine Learning interview questions — page 24 | Vibe Interview