Question 1

What is the difference between supervised and unsupervised learning?

Accepted Answer

Supervised learning uses labeled data to predict outcomes, while unsupervised learning finds hidden patterns or intrinsic structures in input data without labeled responses.

Question 2

Explain the bias-variance tradeoff in machine learning.

Accepted Answer

Bias is the error due to overly simplistic assumptions, and variance is the error due to too much complexity. A good model balances both to minimize total error.

Question 3

What is precision, recall, and F1-score?

Accepted Answer

Precision: TP / (TP + FP), Recall: TP / (TP + FN), F1-score: Harmonic mean of precision and recall. Used in classification tasks to measure performance.

Question 4

What is the difference between bagging and boosting?

Accepted Answer

Bagging trains multiple independent models in parallel and averages their predictions. Boosting trains models sequentially, each trying to correct the previous one's errors.

Question 5

Explain how a decision tree splits data.

Accepted Answer

A decision tree splits data at each node using metrics like Gini Index or Information Gain to maximize class purity in child nodes.

Question 6

What is the difference between classification and regression?

Accepted Answer

Classification predicts discrete labels (e.g., spam/not spam), while regression predicts continuous values (e.g., house price).

Question 7

What is overfitting and how can you prevent it?

Accepted Answer

Overfitting occurs when a model learns noise instead of the underlying pattern. Prevention: cross-validation, regularization, pruning, more data, simpler models.

Question 8

How does k-nearest neighbors (KNN) work?

Accepted Answer

KNN classifies a data point by majority vote among its k nearest neighbors based on distance (e.g., Euclidean). No training phase, but prediction is O(n).

Question 9

Explain how support vector machines (SVM) work.

Accepted Answer

SVM finds the hyperplane that maximizes the margin between classes. It uses kernel trick to handle non-linear data by mapping to higher dimensions.

Question 10

What is the difference between L1 and L2 regularization?

Accepted Answer

L1 (Lasso) adds absolute values of coefficients, can shrink some to zero (feature selection). L2 (Ridge) adds squared values, shrinks coefficients but keeps all.

Machine Learning Interview Questions & Answers

What is the difference between supervised and unsupervised learning?

Explain the bias-variance tradeoff in machine learning.

What is precision, recall, and F1-score?

What is the difference between bagging and boosting?

Explain how a decision tree splits data.

What is the difference between classification and regression?

What is overfitting and how can you prevent it?

How does k-nearest neighbors (KNN) work?

Explain how support vector machines (SVM) work.

What is the difference between L1 and L2 regularization?

What is the ROC curve and AUC?

Explain cross-validation and its types.

What is gradient boosting and how does it differ from random forest?

Explain the concept of neural networks and backpropagation.

What is the difference between batch gradient descent and stochastic gradient descent?

Prepare for Your Next Interview