Have an interview for a entry level machine learning position. Was wondering what some potential questions could be like as I’ve never had an interview related to ML before
Overfitting vs underfitting, compare pros and cons of different models, supervised vs unsupervised models, how would you diagnose why a model was underperforming
1. Missing value imputation - why, how, things to check 2. Outlier detection techniques - why, how, things to check 3. Step by step process you take to analyze a dataset 4. Basic data quality checks you perform 5. Multicollinearity - detection, why is it a problem, why am I bothered if predictive power of the algorithm is good 6. How to determine variable importance in random forest, and more so, in ensemble models such as random forest + gradient boosting 7. I was given a scatter plot for a dataset, and asked to draw the tentative output of a classification decision tree, and justify it 8. Assumptions of linear regression model 9. Techniques to reduce overfitting, techniques to improve predictive power of the model 10. Model comparison parameters All the best!
Hey ygkc82, sorry I just noticed you are applying for entry level position. I applied for a position or two above that, so my previous comment is based on the questions I was asked. Difficulty level of your questions may be slightly lower than this. Also, I was asked to do some basic coding in SQL and R/SAS/Python.
Thanks for all the examples! This is like an entry level engineering/ machine learning position so I think the questions would likely be easier but it’s better to be over prepared
Design a machine learning model for when do i get up from bed to show up at work on time.
1. Explain bagging and boosting. How are they different? 2. What are the assumptions of OLS? What happens if the assumptions are violated? 3. What is cointegration? 4. What are spurious correlations between 2 time series? 5. What is the null space of a matrix? How do I compute vectors spanning the null space? 6. What is a conjugate prior? 7. What are MAP and MLE in Bayesian estimation? 8. What does the Viterbi algorithm do? 9. What does the EM algorithm do? 10. How does matrix factorization work in a recommender system?
Implement a linear regression algorithm.