Supervised Learning

Question 1

What is Naive Bayes classification?

Answer 1

Naive Bayes is a probabilistic classifier. It is based on probability models that incorporate strong independence assumptions…therefore they are considered as naive. It is one of the simple and most effective classification algorithms which helps in building the fast machine learning models that can make quick predictions. It makes predictions based on the probability of an object.

Question 2

What is the formula for conditional probability assuming independent events?

Answer 2

P(A | B) = P(A,B) / PB

Question 3

Why do you need to standardize your variables when using kNN?

Answer 3

kNN is measuring the distance between data points. If variables aren’t on the same scale, variables with larger scale numbers will disproportionately impact the distance calculations.

Question 4

When will a parametric approach such a least-squares linear regression outperform non-parametric approaches such as KNN regression.

Answer 4

Simple; when the parametric form that has been chosen is a close approximation of the true model form.

Question 5

When it comes to the test error rate, why do we take out predictors that do not appear to be significantly related to the outcome variable?

Answer 5

Using predictors that have no relationship with the response tends to cause a deterioration in the test error rate since such predictors cause an increase in variance without a corresponding decrease in bias