#regression-metrics

7 questions from Evaluation Metrics

Timed test

7 questions · 7 min · score and explanations at the end

Q 1 / 7Score 0 / 0

Shuffle questions

Question 1: Single choice

mediumAI-checkedEvaluation Metrics

The table shows 10-fold cross-validation results of a regressor, scored with $R^2$ (the default regression score in scikit-learn):

fold	test_score	train_score
0	−0.003547	0.0
1	−0.001266	0.0
2	−0.011767	0.0
3	−0.006744	0.0
4	−0.076533	0.0
5	−0.003133	0.0
6	−0.000397	0.0
7	−0.003785	0.0
8	−0.001740	0.0
9	−0.000117	0.0

Which regressor most likely produced these scores?

A baseline that always predicts the median of the training targets1
A support vector regressor with an RBF kernel2
A support vector regressor with a linear kernel3
A baseline that always predicts the mean of the training targets4

Keys: 1–9 select · Enter check / next