Practice 50 chapter-wise MCQs covering machine learning, model assessment, descriptive statistics, SQL, data visualization, and data storytelling for FBISE HSSC-II Computer Science.
1. Which field combines computing, statistics, and domain knowledge to extract insights from data?
A) Data science B) Data science C) Word processing D) Operating systems
2. What is a machine learning model primarily designed to do?
A) Replace all databases B) Learn patterns from data C) Increase monitor size D) Compile HTML only
3. How does machine learning differ from a rule-based algorithm?
A) It always uses fixed rules only B) It can learn patterns from data C) It can learn patterns from data D) It never produces predictions
4. What is a feature in a machine learning dataset?
A) A final report B) An input variable used by a model C) A database password D) An input variable used by a model
5. What is the purpose of feature engineering?
A) To create or transform useful input features B) To create or transform useful input features C) To replace the operating system D) To format a hard disk
6. What is a train-test split used for?
A) To duplicate a database B) To train a model on one portion and evaluate it on another C) To compress an image D) To install Python
7. Why should test data generally remain separate from training data?
A) To increase file size B) To evaluate performance on unseen data C) To evaluate performance on unseen data D) To avoid using statistics
8. What does model assessment measure?
A) Screen resolution B) How well a model performs on appropriate data C) Keyboard speed D) How well a model performs on appropriate data
9. What is a predictive outcome?
A) An outcome estimated by a model B) A guaranteed causal explanation C) A database table name D) A programming keyword
10. Why is prediction not necessarily the same as causality?
A) Prediction always proves causality B) A relationship useful for prediction does not by itself prove cause and effect C) Causality cannot involve data D) Models cannot make predictions
11. What is supervised learning?
A) Learning without any data B) Learning from data containing target outcomes C) Learning from data containing target outcomes D) Drawing charts manually
12. What is unsupervised learning?
A) Finding patterns in data without labeled target outcomes B) Training only on labeled answers C) Writing SQL commands D) Finding patterns in data without labeled target outcomes
13. What is a classification problem?
A) Predicting a category or class B) Predicting only continuous values C) Sorting files by name D) Creating a database schema
14. What is a regression problem?
A) Predicting a numerical value B) Predicting a numerical value C) Creating hyperlinks D) Encrypting a file
15. What is a model parameter?
A) A value learned or fitted during model training B) A chart legend C) A value learned or fitted during model training D) A keyboard setting
16. What is a hyperparameter?
A) A setting chosen to control the learning process B) A value always predicted by the model C) A file extension D) A setting chosen to control the learning process
17. What is hyperparameter tuning?
A) Searching for suitable settings to improve model performance B) Deleting the training set C) Changing the monitor D) Writing a web page
18. What is overfitting?
A) When a model has no data B) When a model fits training data too closely and performs poorly on new data C) When a database has many rows D) When a chart has two axes
19. What is underfitting?
A) When a model is too simple to capture important patterns B) When a model memorizes every training example C) When a model is too simple to capture important patterns D) When data is visualized
20. Why is model performance evaluated on data not used for fitting?
A) To make the model larger B) To estimate generalization to unseen cases C) To remove all errors from data D) To estimate generalization to unseen cases
21. What does accuracy measure in a classification task?
A) The proportion of predictions that are correct B) The proportion of predictions that are correct C) The number of database tables D) The size of a chart
22. What is precision?
A) The proportion of predicted positives that are actually positive B) The proportion of predicted positives that are actually positive C) The number of features D) The average of every input column
23. What is recall?
A) The proportion of actual positives correctly identified B) The number of false positives only C) The proportion of actual positives correctly identified D) The size of a dataset
24. What is a confusion matrix used for?
A) Summarizing classification prediction outcomes B) Creating a spreadsheet formula C) Storing passwords D) Summarizing classification prediction outcomes
25. What is mean absolute error (MAE)?
A) The average absolute difference between predictions and actual values B) The number of correct classes C) A database constraint D) A visualization type
26. What is a dataset?
A) A collection of related data used for analysis or modeling B) A collection of related data used for analysis or modeling C) A monitor setting D) A network cable
27. What is data preprocessing?
A) Preparing raw data for analysis or modeling B) Writing only HTML C) Preparing raw data for analysis or modeling D) Creating a keyboard layout
28. Why can missing values be a problem?
A) They always improve accuracy B) They can affect analysis and model training C) They make every model causal D) They can affect analysis and model training
29. What is data cleaning?
A) Detecting and correcting or handling inaccurate, incomplete, or inconsistent data B) Deleting all useful observations C) Creating only images D) Changing the CPU
30. What is data visualization?
A) Representing data graphically to communicate patterns and insights B) Representing data graphically to communicate patterns and insights C) Compiling Python D) Replacing a dataset
31. What is data storytelling?
A) Combining data, visuals, and explanation to communicate an insight B) Storing data without interpretation C) Combining data, visuals, and explanation to communicate an insight D) Creating passwords
32. Why should a visualization have a clear purpose?
A) To use more colors only B) To help viewers understand the intended message or pattern C) To increase database size D) To help viewers understand the intended message or pattern
33. Which chart is commonly suitable for showing change over time?
A) Line chart B) Line chart C) Scatter-free table D) Database schema
34. Which chart is commonly useful for comparing categories?
A) Bar chart B) Bar chart C) Database key D) Audio file
35. Which visualization is useful for examining the relationship between two numerical variables?
A) Scatter plot B) Pie chart only C) Scatter plot D) Text editor
36. What does descriptive statistics do?
A) Summarizes important characteristics of data B) Proves every causal relationship C) Creates computer hardware D) Summarizes important characteristics of data
37. What is the mean?
A) The sum of values divided by their number B) The sum of values divided by their number C) The most frequent value only D) The largest value only
38. What is the median?
A) The middle value after ordering the data B) The middle value after ordering the data C) The largest value D) The number of rows
39. What is the mode?
A) The most frequently occurring value B) The smallest value C) The most frequently occurring value D) The number of columns
40. What does SQL stand for?
A) Simple Question Language B) Structured Query Language C) System Query Link D) Structured Query Language
41. What is SQL mainly used for?
A) Managing and querying relational databases B) Editing photographs C) Controlling a monitor D) Writing operating system drivers only
42. What does SELECT do in SQL?
A) Deletes a database B) Retrieves specified data from a database C) Creates a password D) Changes screen brightness
43. What does WHERE do in an SQL query?
A) Filters rows according to a condition B) Sorts only columns alphabetically C) Filters rows according to a condition D) Creates a chart automatically
44. What does GROUP BY help accomplish?
A) It groups rows with common values for aggregate analysis B) It encrypts a database C) It creates a new operating system D) It groups rows with common values for aggregate analysis
45. What is an aggregate function?
A) A function that summarizes multiple rows into a value B) A command for formatting text C) A networking protocol D) A file compression method
46. What is a database schema?
A) A description of the structure of a database B) A description of the structure of a database C) A chart color D) A Python comment
47. Why is data visualization useful in data science?
A) It can reveal patterns, trends, and comparisons more clearly B) It guarantees causality C) It can reveal patterns, trends, and comparisons more clearly D) It prevents all errors
48. What should be considered when selecting a model performance metric?
A) Only the model name B) The type of problem and the consequences of errors C) The computer brand D) The type of problem and the consequences of errors
49. Why can multiple views of the same dataset be valuable?
A) Different summaries or visualizations can reveal different insights B) They always produce identical conclusions C) They eliminate the need for analysis D) They make every prediction causal
50. What is the main goal of applying machine learning to a real-world problem?
A) To use data to produce useful predictions, classifications, or insights B) To use data to produce useful predictions, classifications, or insights C) To replace all human decisions D) To store files without analysis
This chapter is prepared with reference to the official FBISE HSSC-II Computer Science Assessment Framework and National Curriculum. It covers CS-12-D-01, including machine learning model building and performance assessment, and CS-12-D-02, including data storytelling, descriptive statistics, SQL, and data visualization.