Train-Test Split Quiz

Froggy Jumps

(2)

Played 9

Create copy

About this activity

ML data split basics

Created by

Suba K

India

Download the paper version to play

Top 10 results

#	Player	Accuracy	time
1	Ramya April 17, 2026	% 100	01:58
2	Nethra April 17, 2026	% 90	00:57
3	Neeeeehhhhhhhaaaaaa April 17, 2026	% 90	04:45
4	Kavi April 17, 2026	% 80	01:34
5	Nandy April 17, 2026	% 60	03:12
6	Geetha April 17, 2026	% 60	03:18
7	Shaaaa April 17, 2026	% 40	02:14
8	banu April 17, 2026	% 40	03:10
9	Suba April 16, 2026	% 30	00:34

Do you want to stay in the Top 10 of this game? Log in to identify yourself.

Make your own free game from our game creator

Compete against your friends to see who gets the best score in this game

Make challenge

pizza

Lorelay Tyana

Romania

(258)

joc despre pizza
Bill of Rights Game - The Constitutionalist

Doni The Don

United States

(89)

Test your knowledge on the Bill of Rights. A fun way to test your knowledge and focus on where you need to improve.
The Integumentary System

Breanna Nesbitt

United States

(58)

Functions and Structures of the skin
Phlebotomy Order of Draw Quiz

Pamela Chapman

United States

(59)

Test your knowledge of the order of draw in Phlebotomy with these 10 questions!
Ethos, Pathos, and Logos Quiz

Kristine Vester

United States

(131)

Test your knowledge of ethos, pathos, and logos with these 10 questions on examples of persuasive techniques.


Froggy Jumps Train-Test Split QuizOnline version ML data split basics by Suba K 1 What is the main purpose of a train-test split in machine learning? a To evaluate model performance on unseen data b To reduce compute time c To increase training data size 2 What is a typical train/test split ratio for a common approach? a 80/20 (train/test) b 50/50 c 90/10 3 What does data leakage mean in the context of train-test splits? a Training data influences the test results b Test data information influences the training process c Split occurs after training 4 What is a stratified split designed to preserve? a The order of data points b The original class distribution in both sets c The feature correlations 5 Why should you shuffle data before splitting? a To ensure representative samples in both sets b To reduce data size c To increase model bias 6 When is cross-validation preferred over a single train/test split? a When data is limited and you want a robust estimate b When there is plenty of data c Only for unsupervised tasks 7 What is a risk of using a very small test set? a High variance in the performance estimate b Overfitting the training set c Too much training data 8 How should imbalanced datasets be handled in train/test splits? a Ignore the imbalance b Always oversample the minority class c Use stratified sampling to preserve class proportions 9 Give an example of data leakage in preprocessing. a Splitting first then fitting on train only b Applying random augmentation after split c Fitting a scaler on the full dataset before splitting 10 What does a hold-out validation refer to? a A single train/test split set aside for evaluation b Bootstrapped resampling c Multiple folds of data partitioning

Froggy Jumps

Train-Test Split QuizOnline version

ML data split basics

by Suba K

What is the main purpose of a train-test split in machine learning?

To evaluate model performance on unseen data

To reduce compute time

To increase training data size

What is a typical train/test split ratio for a common approach?

80/20 (train/test)

50/50

90/10

What does data leakage mean in the context of train-test splits?

Training data influences the test results

Test data information influences the training process

Split occurs after training

What is a stratified split designed to preserve?

The order of data points

The original class distribution in both sets

The feature correlations

Why should you shuffle data before splitting?

To ensure representative samples in both sets

To reduce data size

To increase model bias

When is cross-validation preferred over a single train/test split?

When data is limited and you want a robust estimate

When there is plenty of data

Only for unsupervised tasks

What is a risk of using a very small test set?

High variance in the performance estimate

Overfitting the training set

Too much training data

How should imbalanced datasets be handled in train/test splits?

Ignore the imbalance

Always oversample the minority class

Use stratified sampling to preserve class proportions

Give an example of data leakage in preprocessing.

Splitting first then fitting on train only

Applying random augmentation after split

Fitting a scaler on the full dataset before splitting

What does a hold-out validation refer to?

A single train/test split set aside for evaluation

Bootstrapped resampling

Multiple folds of data partitioning

You can integrate the game into an LMS compatible with LTI 1.1 or LTI 1.3 such as Canvas, Moodle, or Blackboard. This way, the scores will be automatically saved into the platform’s gradebook.

Train-Test Split Quiz

Froggy Jumps

About this activity

Created by

Download the paper version to play

Top Games

Froggy Jumps

pizza

Froggy Jumps

Bill of Rights Game - The Constitutionalist

Froggy Jumps

The Integumentary System

Froggy Jumps

Phlebotomy Order of Draw Quiz

Froggy Jumps

Ethos, Pathos, and Logos Quiz

Froggy Jumps

Train-Test Split QuizOnline version

by Suba K

What is the main purpose of a train-test split in machine learning?

What is a typical train/test split ratio for a common approach?

What does data leakage mean in the context of train-test splits?

What is a stratified split designed to preserve?

Why should you shuffle data before splitting?

When is cross-validation preferred over a single train/test split?

What is a risk of using a very small test set?

How should imbalanced datasets be handled in train/test splits?

Give an example of data leakage in preprocessing.

What does a hold-out validation refer to?

		%
	Anonymous	%
		%
		%