Unit 1 - Practice Quiz

INT234 50 Questions
0 Correct 0 Wrong 50 Left
0/50

1 What is the primary goal of Predictive Analytics?

A. To predict future outcomes based on historical data
B. To describe what happened in the past
C. To store large amounts of data
D. To prescribe the best course of action

2 Which of the following is NOT a phase in the standard predictive analytics lifecycle?

A. Hardware Manufacturing
B. Model Building
C. Deployment
D. Data Preparation

3 Descriptive Analytics differs from Predictive Analytics because Descriptive Analytics focuses on:

A. Summarizing past events
B. Forecasting future trends
C. Creating machine learning models
D. Optimizing decision making

4 Which of the following is a common application of Predictive Analytics?

A. Credit scoring
B. Real-time operating system scheduling
C. Creating a database schema
D. Generating an annual report

5 In the context of Machine Learning, what is 'Training Data'?

A. Data used to teach the algorithm patterns
B. Data that has been corrupted
C. Data used to evaluate the final model
D. Future data that has not occurred yet

6 Which type of analytics answers the question 'What should we do about it'?

A. Diagnostic Analytics
B. Predictive Analytics
C. Prescriptive Analytics
D. Descriptive Analytics

7 Machine Learning is best described as:

A. Data storage optimization
B. Strictly using statistical regression only
C. Hard-coding rules for every possible scenario
D. A subset of AI where computers learn from data without explicit programming

8 What is the 'Target Variable' in a predictive model?

A. The index of the dataset
B. The variable being predicted
C. The variable used to predict
D. The noise in the data

9 Which of the following is a type of Supervised Learning?

A. Clustering
B. Dimensionality Reduction
C. Regression
D. Association Rule Learning

10 In Supervised Learning, the dataset must contain:

A. Unlabeled data
B. Only input features
C. Only images
D. Labeled data (Input features and Output labels)

11 Unsupervised Learning differs from Supervised Learning because it:

A. Finds hidden patterns in unlabeled data
B. Is only used for text data
C. Uses labeled data
D. Predicts a specific target

12 Predicting the price of a house based on its square footage is an example of:

A. Reinforcement Learning
B. Clustering
C. Regression
D. Classification

13 Predicting whether an email is 'Spam' or 'Not Spam' is an example of:

A. Classification
B. Clustering
C. Principal Component Analysis
D. Regression

14 Which of the following is an Unsupervised Learning algorithm?

A. Decision Trees
B. Linear Regression
C. K-Means Clustering
D. Logistic Regression

15 What is the main objective of Clustering?

A. To predict a continuous value
B. To group similar data points together
C. To reduce the number of rows in a table
D. To classify data into known categories

16 Reinforcement Learning involves an agent that learns by:

A. Interacting with an environment and receiving rewards or penalties
B. Mimicking a teacher
C. Cleaning database records
D. Analyzing static clusters

17 Which of the following is a common issue where a model performs well on training data but poorly on new data?

A. Underfitting
B. Overfitting
C. Clustering
D. Normalization

18 What is the first step in Data Preprocessing?

A. Data Cleaning
B. Feature Scaling
C. Model Training
D. Hyperparameter Tuning

19 Garbage In, Garbage Out (GIGO) implies that:

A. Computer hardware needs regular cleaning
B. Poor quality input data leads to poor quality model output
C. We should delete all data
D. More data always results in better models

20 Which technique is used to handle missing values in a dataset?

A. Imputation
B. Clustering
C. Overfitting
D. Regression

21 What is the purpose of 'Feature Scaling'?

A. To remove missing values
B. To increase the number of features
C. To bring all features to a similar scale or range
D. To convert text to numbers

22 Standardization (Z-score normalization) transforms data to have:

A. A mean of 100
B. A mean of 0 and standard deviation of 1
C. No negative numbers
D. A range between 0 and 1

23 Which preprocessing technique is used to convert categorical variables into numerical format?

A. Scaling
B. Imputation
C. Encoding
D. Sampling

24 One-Hot Encoding helps in handling:

A. Nominal categorical data
B. Missing values
C. Continuous variables
D. Outliers

25 An outlier is defined as:

A. A categorical variable
B. A data point that differs significantly from other observations
C. A value that is exactly the mean
D. A missing value

26 Which method is commonly used to detect outliers?

A. Gradient Descent
B. Confusion Matrix
C. Pie Chart
D. Box Plot

27 Dimensionality Reduction aims to:

A. Increase the number of variables
B. Remove all categorical variables
C. Reduce the number of input variables while retaining important information
D. Create more rows in the dataset

28 PCA (Principal Component Analysis) is a technique used for:

A. Data Imputation
B. Dimensionality Reduction
C. Supervised Classification
D. Reinforcement Learning

29 Why do we split data into Training and Testing sets?

A. To remove outliers
B. To evaluate the model's performance on unseen data
C. To make the dataset smaller
D. To train two different models

30 Underfitting occurs when:

A. The model is too complex
B. The model captures noise
C. The model is too simple to capture the underlying structure of the data
D. The training data is perfect

31 Which of the following is NOT a data preprocessing step?

A. Data Cleaning
B. Hypothesis Testing
C. Data Transformation
D. Feature Selection

32 Min-Max Scaling transforms data into which range?

A. [0, 100]
B. [-1, 1]
C. [-infinity, +infinity]
D. [0, 1]

33 In a dataset, a row usually represents:

A. A feature
B. A statistical summary
C. An observation or instance
D. A label

34 Market Basket Analysis is an application of which learning type?

A. Classification
B. Supervised Learning
C. Association Rule Learning
D. Regression

35 Which of the following describes 'Feature Selection'?

A. Creating new features from existing ones
B. Scaling features
C. Handling missing values
D. Selecting the most relevant features to improve model performance

36 Noise in data refers to:

A. Missing values
B. Meaningless or random variance in the data
C. Categorical labels
D. Duplicate rows

37 Which of the following is a quantitative variable?

A. Zip Code
B. Age
C. Gender (Male/Female)
D. Color (Red/Blue)

38 Label Encoding is best used when:

A. There are missing values
B. The data is continuous
C. The categorical feature is ordinal (has an inherent order)
D. The categorical feature has no order

39 The process of converting raw data into a clean dataset is often called:

A. Data Architecture
B. Data Wrangling/Munging
C. Data Mining
D. Data Visualization

40 Which of these is a supervised learning algorithm used for classification?

A. PCA
B. Logistic Regression
C. K-Means
D. Apriori

41 If a dataset has duplicate records, the preprocessing step required is:

A. Encoding
B. Deduplication
C. Imputation
D. Normalization

42 The 'Curse of Dimensionality' refers to problems caused by:

A. Inaccurate labels
B. Too many missing values
C. Too much processing power
D. Too many features (variables) relative to the number of observations

43 Which variable type requires dummy variables creation during preprocessing?

A. Binary
B. Categorical
C. Ordinal
D. Numerical

44 Semi-supervised learning uses:

A. A small amount of labeled data and a large amount of unlabeled data
B. Only unlabeled data
C. Only labeled data
D. Reinforcement signals

45 What is the result of 'Data Transformation'?

A. Data is collected
B. Data is deleted
C. Data is visualized
D. Data is converted into a format suitable for modeling

46 Predicting the temperature for tomorrow is a:

A. Preprocessing task
B. Classification task
C. Regression task
D. Clustering task

47 Customer segmentation usually relies on which type of learning?

A. Supervised Learning
B. Regression
C. Unsupervised Learning (Clustering)
D. Reinforcement Learning

48 Which of the following represents 'Structured Data'?

A. Relational database tables
B. Emails
C. Audio recordings
D. Video files

49 Balanced data refers to:

A. Data where all values are the same
B. Data with no missing values
C. Data that has been scaled
D. Data where the target classes are represented approximately equally

50 Binning is a preprocessing technique used to:

A. Remove outliers
B. Normalize data
C. Fill missing values
D. Convert continuous variables into categorical intervals