An initial round (background/ profile based), a simple classification problem as homework, a technical interview (mostly based on how the solution was framed for the homework), an interview with a non-technical person, and a final round with their co-founder. 1. Why does multicollinearity happen in regression? 2. Working of boosted trees 3. Types of regularization 4. Overfitting and underfitting
Anonymous
1. when the independent variable are correlated in a regression model. 2. in this each new tree isa fit on modified version of the original data set . 3. Lasso and Ridge Regularization. 4. Good performance on training data and bad performance for the other one.
Check out your Company Bowl for anonymous work chats.