#information-gain

3 questions from Decision Trees & Ensembles

Timed test

3 questions · 3 min · score and explanations at the end

Q 1 / 3Score 0 / 0

Shuffle questions

Question 1: Single choice

easyAI-checkedDecision Trees & Ensembles

A frog's jumps were recorded with two binary features:

Observation	Green	Rain	Jump
$x_1$	1	0	+
$x_2$	1	1	+
$x_3$	1	0	+
$x_4$	1	1	+
$x_5$	1	0	+
$x_6$	0	1	+
$x_7$	0	0	−
$x_8$	0	1	−

Without computing information gains, which feature should a decision tree split on first?

Green, because Green = 1 gives a pure node of five positives1
Rain, because it splits the data into two equal halves2
Either one, because both are binary3
Neither, because no single split gives two pure nodes4

Keys: 1–9 select · Enter check / next