Software Engineering › Key terms › Y12 Software Automation › Training data and test data
Training data and test data
Term Check Y12 Software Automation
Definition
Training data is used to teach the model; separate test data checks how well it works on data it has not seen.
Example: Hold back 20% of the data for testing.
Check this one: Standard ML practice; check the exact wording against your class notes.
Where it is used in the test
Syllabus area: Y12 Software Automation.
Question types it can appear in
- Multiple choice: Pick the option that matches the definition or example.
- Short answer: Define, outline or explain it and tie it to the scenario.
- Fill in the blanks: Choose this term to complete a statement or table.
Where it has appeared in the paper
Software Automation (Part B). Part letters follow each paper’s own layout.
Related past questions
- Sample exam Q23b (3 marks): Linear regression v K-nearest neighbour Software Automation (Part B) · 3 marks
These are the questions the flashcard set links to this term. Open each one and compare your answer with its marking criteria.
Study links
- Flashcard: Training data and test data in Software Automation (Year 12) · study that set
- Memorise: Models of training ML
How to use it in an answer
A model sentence
“Training data is used to teach the model; separate test data checks how well it works on data it has not seen.” Then apply it: Hold back 20% of the data for testing.
In a short answer, give the definition in your own words first, then tie it to the situation in the question. Do not copy the example above unless it fits the scenario.
Command words used with it
- Compare: Show how things are similar or different. (Sample exam Q23b (3 marks): Linear regression v K-nearest neighbour)
Technique for the question types
- Multiple choice: Read all four options, rule out wrong ones, pick one; no penalty for guessing so never leave blank.
- Short answer: One clear point per mark, use the stimulus and course terms, and answer the command word.
- Fill in the blanks: Choose the right word from a list; use exact syllabus terms.
What the marking guidelines and feedback say
Some school notes list KNN as unsupervised: that is wrong. NESA's sample answer treats KNN as supervised.
Worked answers from the marking guidelines
Sample exam Q23b (3 marks): Linear regression v K-nearest neighbour (3 marks): criteria and sample answer
Criteria
3: Compares linear regression and KNN. 2: Outlines features of one or both. 1: Some relevant information.
Sample answer
Linear regression and K-nearest neighbours (KNN) are both supervised learning algorithms that make predictions from labelled data. The key difference is how they handle data: linear regression assumes a linear relationship between input features and the target variable, while KNN makes predictions based on the closest 'K' training examples, allowing it to handle more complex, non-linear patterns. However, KNN can be more computationally expensive than linear regression and is usually slower.
Common mistakes
- Check the sources: Standard ML practice; check the exact wording against your class notes.
- Use the term exactly as the syllabus words it, then link it to the scenario in the question; the 2025 feedback repeatedly rewards using the stimulus.
- Answer the command word: outline gives main points only, explain gives a reason or cause, discuss gives both sides.
Related terms
Same group in the syllabus: Supervised learning · Unsupervised learning · Semi-supervised learning · Reinforcement learning