中文（繁體）
中文（简体）
English
S6 ICT: Artificial Intelligence and Machine Learning – Practice Paper 1 (Foundation, 10 Questions)
S6 ICT: Artificial Intelligence and Machine Learning – Practice Paper 1 (Foundation, 10 Questions)
Paper one builds the basics: reading the four cells of a confusion matrix, then accuracy 91.0%, precision 72.0%, recall 90.0%, F1 80.0% and specificity 91.25% – ten items with answers and notes.
Quick answer Start every classification question by counting the four cells: the two correct cells give accuracy, and the two positive predictions give the precision denominator.
01 Paper details (check answers afterwards)
| Item | Detail |
|---|---|
| Questions | 10 questions |
| Suggested time | 25 minutes |
| Difficulty mix | Foundation 4 · Intermediate 3 · Challenge 2 · Error redo 1 |
| Chapter | Chapter: S6 ICT | Artificial Intelligence and Machine Learning |
| Level | Foundation |
02 Questions (10 items)
- FoundationA spam filter gives a confusion matrix: 36 spam mails flagged as spam, 14 normal mails wrongly flagged, 4 spam mails missed, and 146 normal mails passed. How many mails are in the test set?
- FoundationWhat does the cell holding 36 represent?
- FoundationWhich category does the cell holding 14 belong to?
- FoundationWhich category does the cell holding 4 belong to?
- IntermediateWhat is the accuracy of this filter?
- IntermediateAfter raising the threshold to cut false alarms, 50 mails are flagged as spam and 36 of them are correct. What is the precision?
- IntermediateThere are 40 spam mails in total and 36 are caught. What is the recall?
- ChallengeUsing a precision of 72.0% and a recall of 90.0%, find the F1 score.
- ChallengeSpecificity is the share of normal mails that are correctly passed. What is the specificity of this filter?
- Error redoA student computes accuracy as (36+4) divided by 200, obtaining 20.0%. What is wrong?
03 Answers and one-line notes
| # | Answer | One-line note |
|---|---|---|
| 1 | 200 mails. | 36+14+4+146 = 200, so the four cells add up to the whole test set. |
| 2 | A true positive, meaning spam that was correctly caught. | The prediction is positive and the actual label is positive, which is a true positive. |
| 3 | A false positive, a normal mail wrongly blocked. | The prediction is positive but the actual label is negative, which is a false alarm. |
| 4 | A false negative, spam that reached the inbox. | The prediction is negative but the actual label is positive, which is a miss. |
| 5 | 91.0%. | (36+146) divided by 200 is 182 over 200, which is 0.91. |
| 6 | 72.0%. | 36 divided by (36+14) is 36 over 50, which is 0.72. |
| 7 | 90.0%. | 36 divided by (36+4) is 36 over 40, which is 0.90. |
| 8 | 80.0%. | Two times 0.72 times 0.90 is 1.296, divided by 1.62 gives 0.80. |
| 9 | 91.25%. | 146 divided by (14+146) is 146 over 160, which is 0.9125. |
| 10 | The numerator must be the two correct cells, 182 in total. | Accuracy counts only the cells that are correct, namely 36 and 146, giving 182. |
04 What to do after marking
- After marking, redo only the wrong items and write down which step went wrong (formula, unit, or misread number).
- Repeat the same item two days later; move to the next paper only when both attempts are correct.
- Parents only need the answer and note columns; there is no need to explain every item.
Find a tutor freeTutor Registration →
Questions and answers are written originally by the TutorZone team and are not taken from any school, publisher or examination authority paper. Every value is checked by computer.