2019-12-31 Two Data Science Interview Questions that you must be able to answer

In the interest of not failing twice in the same spot and making yourself useful to others, this post of mine is dedicated to people who want to follow their passion of becoming/improving as a Data Scientist. I strongly believe that you must keep giving interviews even if you are not looking for a career change, just because your learn a great deal when you give interviews. There is no faster way of learning. Data Science is a field that requires constant improvement in your skills set, while developing basic concepts in Machine Learning algorithms on a daily basis. So without further ado, let us dive straight into some questions and answers that you might useful in your next interview.

Question 1Can you explain cost function of decision trees?

Answer: Before we answer this question, it is important to note that Decision Trees are versatile Machine Learning algorithms that can perform both classification and regression tasks. Hence their cost functions are also different.

Question 2: How does collinearity affect your models?

Answer: Collinearity refers to a situation where two or more predictor variables are closely related to one another. Figure 2 below shows as example of collinear variables. Variable 2 strictly follows variable 1 with a Pearson correlation coefficient of 1. So obviously one of these variables will behave like noise when fed into machine learning models.

你可能感兴趣的:(2019-12-31 Two Data Science Interview Questions that you must be able to answer)