New
New
Lesson 7 of 8
  • Year 10
  • AQA

Classification

I can explain how AI systems classify data into categories and how classification underpins many AI tasks.

Lesson 7 of 8
New
New
  • Year 10
  • AQA

Classification

I can explain how AI systems classify data into categories and how classification underpins many AI tasks.

These resources will be removed by end of Summer Term 2025.

Switch to our new teaching resources now - designed by teachers and leading subject experts, and tested in classrooms.

These resources were created for remote use during the pandemic and are not designed for classroom teaching.

Lesson details

Key learning points

  1. Classification is a type of ML task where an AI system assigns data into predefined categories or "classes".
  2. The AI classification system is trained on labelled data.
  3. Classification is one of the most fundamental tasks in AI and underpins many real world systems.

Keywords

  • Class - a predefined group used to organise data that machine learning (ML) developers use to train classification models

  • Label - each piece of data is annotated with one or more labels which provide information about that data

Common misconception

A classifier can be improved by providing more training data.

More data doesn't always mean improved predictions. The quality of data provided to a classifier is as important as the quantity.


To help you plan your year 10 computer science lesson on: Classification, download all teaching resources for free and adapt to suit your pupils' needs...

Pupils will probably have come across classifiers, so perhaps lead a classroom discussion about where they may have seen AI classification in real world scenarios.
Teacher tip

Equipment

Licence

This content is © Oak National Academy Limited (2025), licensed on Open Government Licence version 3.0 except where otherwise stated. See Oak's terms & conditions (Collection 2).

Lesson video

Loading...

Prior knowledge starter quiz

Download quiz pdf

6 Questions

Q1.
What is a key feature of supervised learning?

The model is trained with unlabelled data.
The model creates its own data.
The model ignores patterns.
Correct answer: The model is trained with data that has answers provided.

Q2.
Which of the following is most likely to use unsupervised learning?

Correct answer: grouping customers based on shopping behaviour without knowing their preferences
sorting photos into known categories
marking exam papers
predicting tomorrow’s weather using past data

Q3.
What kind of data does unsupervised learning use?

Correct Answer: unlabelled data, unlabelled

Q4.
What is the main goal of clustering in machine learning?

to label every data point with a category
to remove all errors from data
to make the data larger
Correct answer: to group similar items together

Q5.
Arrange these actions for using clustering in unsupervised learning.

1 - Gather unlabelled data.
2 - Find similarities between data points.
3 - Group similar items together.
4 - Analyse the groups for patterns.

Q6.
Match each keyword to its correct definition.

Correct Answer:supervised learning,training a model with labelled data

training a model with labelled data

Correct Answer:unsupervised learning,training a model with unlabelled data

training a model with unlabelled data

Correct Answer:classification,sorting data into pre-set categories

sorting data into pre-set categories

Correct Answer:clustering,grouping data points based on similarities

grouping data points based on similarities

Assessment exit quiz

Download quiz pdf

6 Questions

Q1.
What is the machine learning task called where data is assigned to predefined categories or groups?

Correct Answer: classification

Q2.
Match each keyword to its correct definition.

Correct Answer:class,a predefined group used to organise data

a predefined group used to organise data

Correct Answer:label,information about which category a data point belongs to

information about which category a data point belongs to

Correct Answer:classification,the process of sorting data into categories

the process of sorting data into categories

Correct Answer:classifier,a machine learning model that assigns data to categories

a machine learning model that assigns data to categories

Q3.
What is one reason a classifier might make mistakes?

The model is always perfect.
The classes are clearly separated.
Correct answer: The labels in the data are incorrect.
The computer is new.

Q4.
Why is classification important in AI systems?

Correct answer: It helps AI systems organise data.
It makes data harder to use.
It slows down computer systems.
It is only used for games.

Q5.
Which of the following is not a classification task?

sorting images into categories
predicting whether a message is positive or negative
grouping animals by species
Correct answer: calculating the total price of items in a basket

Q6.
Arrange these steps into the correct order to create a good classifier.

1 - Collect high quality, relevant data.
2 - Label the data accurately.
3 - Train the classifier.
4 - Evaluate performance.
5 - Improve as needed.