Important Questions about ML Algorithms for Interview
Following posts list down questions I encountered while studying, discussing doubts with friends or interviewing for companies
Linear Regression
- When should I use lasso vs ridge?
- In linear regression, when is it appropriate to use the log of an independent variable instead of the actual values?
- Is there an intuitive explanation why multicollinearity is a problem in linear regression?
- When, why, and how the business analyst should use linear regression
- What are the limitations of linear regression modeling in data analysis?
- How would you evaluate a logistic regression model?
- What are some of the advantages and disadvantages of regression analysis?
Support Vector Machine
- How does support vector regression work intuitively?
- The Effects of Hyperparameters in SVM
- What is the influence of C in SVMs with linear kernel?
- How to intuitively explain what a kernel is?
Decision Trees
- What is “entropy and information gain”?
- How is regularization performed on simple decision trees?
- How to tune a Decision Tree?
- What is the weak side of decision trees?
- Gradient Boosting Tree vs Random Forest
- Practical questions on tuning Random Forests
- Gradient in Gradient Boosting
Clustering Algorithms
- Choosing a clustering method
- How to understand the drawbacks of K-means
- Determining the number of clusters in a data set
- https://www-users.cs.umn.edu/~kumar001/dmbook/ch8.pdf
Search
- Is there an industry standard for measuring search relevancy?
- Evaluating Search: Measure It
- MRR vs MAP vs NDCG: Rank-Aware Evaluation Metrics And When To Use Them
Miscellaneos
- Training a decision tree against unbalanced data
- What is the meaning of p values and t values in statistical tests?
- What, precisely, is a confidence interval?
- Why You Should Use Cross-Entropy Error Instead Of Classification Error Or Mean Squared Error For Neural Network Classifier Training
- What is the role of the bias in neural networks?