Why Do You Need to Split a Machine Learning Dataset

question 15

Multiple Choice

Why do you need to split a machine learning dataset into training data and test data?

• A) So you can try two different sets of features
• B) To make sure your model is generalized for more than just the training data
• C) To allow you to create unit tests in your code
• D) So you can use one dataset for a wide model and one for a deep model

---

Definitions:

Numerator

The top number in a fraction, indicating how many parts of a whole are being considered.

Two-tailed Test

A statistical test in which the critical area for rejection of the null hypothesis is on both sides of the distribution.

Variance

A statistical measurement of the spread between numbers in a data set, indicating how far each number in the set is from the mean.

Significantly Less

A statistical term used to indicate that one set of data is considerably lower than another with a level of statistical significance.