Graduate data scientist interview questions shared by candidates
Why do you want to come work in Bristol and sell kebabs? In the Random Forest hyperparameters you're optimising, which prevent overfitting and why? I'm a business person. What's 'random' about Random Forest, and can you explain which variables are predictive of the positive class?
1.Describe the L1 and L2 norms. 2.Be prepared to describe a relevant project that you have worked on. 3. How does K-means algorithm work. 4.Describe an efficient way of separating transaction data in order to get average for each account holder (they are after all fraud detection company), what data structure would you put the data to to retrieve it quickly. 5.Describe how Random forest works and how it is different from DTC.