Amazon Data Scientist interview questions

Amazon day 1 interview questions Explain SVM.Explain about C value in SVM How would you explain Hypothesis testing for a newbie? Are you familiar with overfiiting? There are 4 red balls and 2 blue balls, what's the probability of them not being the same in the 2 picks? A couple has 2 kids where they know that one's a boy, what's the probability of the other kids being a boy? What are some supervised as unsupervised learning? What did you use to remove multicollinearity? Explain what values of VIF you used? What was the time you had a time constraint to make a decision and how did you deal with the situation? Explain overfiting. Explain lambda values. Explain difference between ridge and lasso regression. How else would you reduce overfiting? Explain different time series analysis. What are other time series models other than Arima? What is lstm? Why use lstm? How was lstm used in your experience? (VMWare case study) What was the most challenging part of your project? How was the model useful to marketing team? How did you identify most important variables in the model? (explained forward selection method) What changes would you make if given a chance to your model?(said about xgboost hyperparameter tuning) Question on the grounds of Amazon leadership behavioral. Make sure you study all 14 and for atleast 1 story from your previous experience in STAR(Situation, task, action, result) format. Day 2: Started off by asking me in detailed questions about my internship. Again, he asks a behavioral question based on Amazon leadership principle. Make sure you have scenarios ready for all 14 principles. Coding questions With queries of SQL that I've seen in LeetCode: Create a new column by extracting last 2 characters of a column containing ID of 7 digit long and in string datatype SQL: Select employee ids/names from a table who has the highest salary in the department One hard question regarding the concept of regression towards the mean