Font size
WorksheetsPage 1
Total questions: 110
Worksheet time: 55mins
Which statement best defines data science?
A discipline extracting insights from data using methods
A spreadsheet technique for faster manual calculations
A business role focused only on sales presentations
A single programming language for data storage tasks
Which is an example of structured data?
Handwritten notes scanned as pictures
Rows and columns in a relational database
A folder of mixed images and videos
Free-form customer emails without templates
What describes unstructured data?
Stored as fixed-length numeric arrays
Follows a strict table schema with keys
Validated by SQL primary key constraints
Lacks a predefined format like text or images
Which option best characterizes semi-structured data?
Only numeric fields with uniform units across rows
Completely raw binary signals without tags
Strict rows and columns with datatypes enforced
Some organization without strict schema, e.g., JSON
Which of the following is NOT one of the 5 V's of data?
Velocity
Volume
Veracity
Variety
Validation
The 'Value' in the 5 V's refers to which idea?
Usefulness of data for decision-making
Physical storage capacity of servers
Number of database tables per project
Legal ownership of enterprise datasets
Which fields are combined in data science as described?
Geology, astronomy, and marine biology
Network hardware, cryptography, and optics
Accounting, law, and literary criticism
Statistics, computer science, and domain expertise
Which task sequence aligns with the data science process described?
Collect, analyze, interpret to inform decisions
Design, print, ship to physical warehouses
Encrypt, compress, transmit to satellites
Draft, vote, ratify in government policy
Which example best matches a high Velocity characteristic?
Streaming sensor data arriving every millisecond
Archived tapes read once per fiscal decade
Monthly PDF reports emailed to executives
Annual census datasets published after years
Which scenario illustrates Variety in data?
Sorting a single spreadsheet by two columns
Duplicating one CSV file into three folders
Combining tables, emails, images, and videos
Compressing logs into a single ZIP archive
Which activity best describes data collection in data science?
Aggregating information from databases and APIs
Fixing errors and standardizing file formats
Presenting results using charts for stakeholders
Training models to learn from historical patterns
What is the primary goal of data cleaning?
Communicating insights through dashboards
Building predictive models using algorithms
Gathering records from multiple web sources
Handling missing values and correcting errors
Which task mainly involves statistical methods to uncover patterns and trends?
Machine learning for automated decisions
Data visualization for executive reports
Data collection via API endpoints
Data analysis on prepared datasets
Machine learning in data science is best defined as
Algorithms enabling computers to learn from data
Manual rules crafted by domain experts
Scripts that download files from web pages
Charts that summarize numerical indicators
Data visualization primarily helps with which outcome?
Automatically cleaning noisy and inconsistent fields
Effectively communicating findings to stakeholders
Selecting features for model generalization
Executing SQL queries across multiple tables
An organization wants to reduce uncertainty in strategic choices. Which benefit of data science is most relevant?
Informed decision-making through data-driven insights
Customer insights from behavior and preferences
Operational efficiency by optimizing processes
Forecasting future trends using historical data
A retailer segments customers and tailors recommendations. Which application is most aligned?
Transportation efforts for route optimization
Healthcare domains like medical image analysis
Finance tasks such as fraud detection workflows
E-commerce use cases like recommendation systems
Which scenario best illustrates operational efficiency gained from data science?
Summarizing survey results for executive slides
Identifying bottlenecks to optimize internal processes
Scraping websites to expand a sales database
Encrypting backups to meet compliance policies
A bank aims to spot suspicious transactions early. Which application fits best?
Risk assessment and fraud detection in finance
Genomic analysis and personalized medicine
Customer segmentation and inventory planning
Route planning and maintenance prediction
Transportation companies can use data science to
Optimize routes and predict maintenance needs
Generate synthetic medical imaging datasets
Personalize content in online storefronts
Execute high-frequency trading strategies
Which role primarily focuses on analyzing and interpreting complex data to inform business decisions?
Data Scientist
Machine Learning Engineer
Data Analyst
Data Engineer
Which responsibility best matches a Data Analyst in an organization?
Maintaining distributed compute clusters
Creating visualizations and reports from datasets
Building scalable data pipelines and storage
Designing and deploying learning algorithms
What is the core focus of a Machine Learning Engineer?
Collecting raw data from sensors
Designing and implementing ML models
Statistical reporting for executives
Exploratory data analysis and storytelling
Which role builds and maintains infrastructure for data generation, storage, and processing?
Data Analyst
Machine Learning Engineer
Data Scientist
Data Engineer
Which skill set most directly supports cleaning and transforming raw datasets?
Model serving with TensorFlow Serving
Data manipulation with Pandas and NumPy
Dashboard design in PowerPoint slides
Container orchestration using Kubernetes
A project requires understanding statistical methods and applications. Which skill category is most relevant?
Machine Learning frameworks knowledge
Statistical knowledge and inference
Network security configurations
Programming in assembly language
Which set of tools is primarily used for presenting insights through charts and dashboards?
PyTorch, TensorFlow, JAX
Hadoop, Spark, Kafka
Git, Docker, Kubernetes
Tableau, Power BI, Matplotlib
During the Problem Definition stage, which action clarifies what success looks like and how to measure it?
Set objectives with clear metrics
Acquire data from all sources
Train baseline predictive models
Deploy dashboards to stakeholders
In the data science process, what is the first step before modeling or visualization?
Hyperparameter optimization
Feature selection with PCA
Problem definition and scoping
Model deployment and monitoring
Which programming languages are commonly expected for data science proficiency?
Scala, Julia, and Perl
HTML, CSS, and JavaScript
C, Go, and Rust
Python, R, and SQL
Which task best describes data cleaning in a data science workflow?
Handle missing values and correct inconsistencies
Measure accuracy and F1 score after training
Create visual dashboards and interactive charts
Choose algorithms for classification or regression
What is the primary goal of data transformation during preprocessing?
Select a model based on problem type
Collect datasets from APIs and surveys
Convert data into a suitable analysis format
Validate performance on a separate dataset
Which step focuses on discovering patterns using summary statistics and visualizations?
Performance metrics reporting
Model validation stage
Cross-validation procedures
Exploratory Data Analysis (EDA)
During data exploration, which activity helps understand distributions and relationships?
Creating visual representations of the data
Encoding categorical variables into numbers
Splitting data into training and validation sets
Adjusting model hyperparameters during training
Which action is part of model building rather than evaluation?
Compute RMSE and F1 score
Train the model on the training dataset
Compare accuracy across models
Perform k-fold cross-validation
In model evaluation, what is the purpose of cross-validation?
Normalize features before training models
Visualize trends during EDA
Select algorithms for classification tasks
Assess the model's robustness across folds
Which data source is considered external in data collection?
Enterprise data warehouse tables
Public APIs providing datasets
Internal transaction logs
Company-owned databases
Which metric is most appropriate for evaluating a regression model?
Root Mean Square Error (RMSE)
Precision on positive class
F1 score for classification
Recall on minority class
Why is a separate validation dataset used after training a model?
Encode categories into numerical features
Increase training accuracy with more epochs
Display distributions through histograms
Ensure the model generalizes to unseen data
Which step should occur before selecting algorithms for model building?
Data cleaning and transformation completed
Reporting accuracy and F1 score
Cross-validation of performance metrics
Visualization of final evaluation results
Which activity best describes model deployment in a data science project?
Visualizing results with interactive charts
Selecting features using domain knowledge
Collecting raw data from various sources
Embedding the model into production systems
What is the primary goal of monitoring after deployment?
Eliminate the need for documentation
Increase dataset size for training
Simplify the model architecture
Maintain accuracy through ongoing checks
Communication and reporting mainly involve which task?
Sharing insights with stakeholders clearly
Encrypting datasets for storage
Rewriting algorithms from scratch
Replacing all existing dashboards
Actionable insights are best defined as recommendations that
Automate data collection tasks
Summarize unrelated metrics
Guide decision-making processes
Guarantee zero prediction error
Feedback and iteration primarily help teams to
Reduce monitoring requirements
Avoid stakeholder involvement
Lock models to prevent changes
Refine models based on new input
Documentation in data science should include records of
Methods, data sources, and decisions
Only final model weights
Only raw datasets and IDs
Only presentation slide designs
In healthcare, predictive analytics is used to
Remove the need for lab tests
Replace doctors with robots
Encrypt MRI images with keys
Forecast outbreaks using health records
Personalized medicine in data science involves
Randomizing all clinical decisions
Ignoring electronic health records
Standardizing one protocol for all
Tailoring treatments to patient data
Drug discovery benefits from data science mainly by
Avoiding any predictive modeling
Increasing costs through manual trials
Reducing data availability in labs
Speeding development with simulations
Medical imaging applications of data science commonly include
Blocking clinicians from image access
Using AI to interpret X-rays and MRIs
Deleting images after brief review
Converting scans to plain text only
Which task in finance primarily uses algorithms to execute trades based on market data?
Fraud detection with anomaly rules
Customer segmentation for campaigns
Risk management via credit scoring
Algorithmic trading using market signals
In e-commerce, what is the main goal of recommendation systems?
Reduce server downtime significantly
Suggest products to increase sales
Optimize delivery routes nationwide
Detect fraudulent transactions quickly
Which transportation application focuses on predicting equipment failures before they occur?
Fleet management optimization
Safety enhancements analytics
Predictive maintenance using sensors
Route optimization with traffic
Market basket analysis is best described as:
Detecting fake product reviews
Forecasting long-term stock prices
Understanding purchasing patterns for promotions
Clustering customers by lifetime value
Which finance task uses data to assess creditworthiness and manage risks?
Portfolio rebalancing rules
Risk management analytics
Algorithmic trading bots
Customer segmentation models
Dynamic pricing in retail relies on which inputs?
Manual price tags from staff
GPS coordinates of customers
Market trends and competitor pricing
Only inventory levels today
What is the primary purpose of route optimization in transportation?
Selecting safer vehicle models
Reducing cashier wait times
Determining efficient delivery routes
Measuring driver satisfaction
Customer segmentation mainly helps organizations to:
Encrypt personal data securely
Design faster databases
Create targeted marketing campaigns
Lower cloud storage costs
Precision farming typically uses which data sources?
Retail point-of-sale receipts
Social media likes and shares
High-frequency trading feeds
Sensors and drones on fields
Which approach best improves transportation safety measures?
Discounting fuel through contracts
Analyzing accident data for high-risk areas
Maximizing fleet size across regions
Outsourcing route planning overseas
Which data science application focuses on predicting when machinery will need maintenance to reduce downtime and costs in manufacturing?
Process optimization for productivity gains
Supply chain efficiency for rapid response
Predictive maintenance for equipment servicing
Quality control monitoring for product quality
In manufacturing, analyzing data to streamline operations and respond quickly to market changes best describes which practice?
Process optimization for productivity improvement
Predictive maintenance for equipment health
Supply chain efficiency for operational agility
Quality control for defect detection
What is the primary goal of brand sentiment analysis in marketing?
Extract insights from social interactions
Tailor promotions using purchase history
Measure campaign success over time
Gauge public sentiment using language data
Which marketing application uses data to measure how successful a campaign was to improve future efforts?
Brand sentiment analysis for opinion mining
Campaign effectiveness for performance metrics
Social media analytics for interaction trends
Customer insights for targeted messaging
Public health monitoring with data science primarily helps governments do what?
Improve tax revenue forecasting
Detect fraud in procurement data
Allocate resources using health trends
Increase voter turnout predictions
Fraud detection in government programs commonly relies on analyzing which type of information?
Sensor data from public vehicles
Satellite imagery for asset tracking
Spending data for irregular patterns
Citizen sentiment from social media
Which agricultural application uses historical data to forecast outcomes and improve planning?
Soil quality classification mapping
Yield prediction for crop planning
Pest management timing decisions
Supply chain optimization logistics
A retailer wants to tailor marketing strategies by understanding consumer behavior patterns. Which application fits this need?
Campaign effectiveness for ROI tracking
Social media analytics for engagements
Brand sentiment for opinion trends
Customer insights for behavior analysis
Enhancing the agricultural supply chain by analyzing data for inventory and distribution is best described as what?
Yield prediction for harvest planning
Supply chain optimization in agriculture
Pest management using analytics
Predictive maintenance for tractors
Which approach leverages data from social interactions to inform marketing campaigns and brand strategies?
Brand sentiment from language models
Campaign effectiveness from KPI metrics
Social media analytics from interactions
Customer insights from purchase records
Which type of data analysis is described as the simplest and most commonly used by organizations?
Diagnostic analysis
Predictive analysis
Descriptive analysis
Prescriptive analysis
According to the four-type framework, which analysis focuses on explaining why something happened?
Descriptive analysis
Diagnostic analysis
Predictive analysis
Prescriptive analysis
Which type of analysis is primarily used to forecast what is likely to happen next?
Descriptive analysis
Diagnostic analysis
Predictive analysis
Prescriptive analysis
Which analysis type recommends actions to achieve desired outcomes?
Prescriptive analysis
Predictive analysis
Diagnostic analysis
Descriptive analysis
On the figure illustrating value versus complexity, which analysis appears at the highest end of complexity?
Diagnostic analysis
Descriptive analysis
Prescriptive analysis
Predictive analysis
Businesses commonly use descriptive analysis to generate which artifacts?
Feature engineering pipelines
Model coefficients and p-values
Optimization policies and scenarios
Sales leads and KPI dashboards
Which pair correctly matches analysis type with its primary question?
Descriptive: What happened?
Prescriptive: What happened?
Predictive: What should we do?
Diagnostic: What will happen?
Which statement best contrasts diagnostic and predictive analysis?
Both forecast outcomes; neither explains causes
Diagnostic forecasts outcomes; predictive explains causes
Diagnostic explains causes; predictive forecasts outcomes
Both explain causes; neither forecasts outcomes
In a monthly business context, which task most clearly aligns with descriptive analysis?
Recommending pricing strategies
Forecasting next quarter’s sales
Identifying causal drivers of churn
Summarizing last month’s revenue trends
Which sequence orders the four analysis types from lower to higher complexity as implied by the figure?
Descriptive, Diagnostic, Predictive, Prescriptive
Diagnostic, Descriptive, Prescriptive, Predictive
Predictive, Descriptive, Diagnostic, Prescriptive
Prescriptive, Predictive, Diagnostic, Descriptive
Which analysis emphasizes answering the question 'what has happened?' using past data?
Prescriptive analysis
Descriptive analysis
Diagnostic analysis
Predictive analysis
In descriptive analysis, data from multiple sources may be combined primarily to achieve what goal?
Reduce storage costs
Increase data privacy
Gain meaningful insights
Automate data collection
Diagnostic analysis primarily seeks to answer which question?
Why it happened
How to optimize actions
What has happened
What will happen next
Which example best illustrates diagnostic analysis in sports performance data?
Finding why a player's form rose
Listing last season's averages
Recommending training drills
Predicting next match scores
What role does business intelligence most closely play within diagnostic analysis?
Encrypting sensitive fields
Visualizing basic trends
Collecting raw data
Digging to root causes
Which technique is often used with business intelligence for deeper problem understanding in diagnostic analysis?
Network routing
Distributed computing
Data encryption methods
Machine learning techniques
Predictive analysis emphasizes which forecasting question using past and current data?
Who collected the data
What exactly happened
What is likely to happen
Why did it occur
Which scenario best fits predictive analysis for a cricket board's decision-making?
Explaining a midseason slump
Estimating future player performance
Summarizing last tournament metrics
Designing practice schedules
Which domains are explicitly mentioned as applications of predictive analysis?
Healthcare diagnostics
Network security auditing
Risk and sales forecasting
Database normalization
For descriptive analysis in team sports, what is a typical output from statistical results?
Performance summaries
Root cause reports
Sensor calibration
Action prescriptions
Which type of data analysis recommends actions to address future situations by combining insights from other analyses?
Diagnostic analysis focused on root causes
Descriptive analysis summarizing past events
Prescriptive analysis recommending next steps
Predictive analysis forecasting future trends
What is a key characteristic of prescriptive analysis mentioned here?
Avoids combining multiple analyses
No connection to predictive forecasting
High responsibility with time-intensive decisions
Low responsibility and minimal time needs
Prescriptive analysis primarily aims to do which of the following?
Prescribe actions to avoid future problems
Explain why anomalies occurred
Describe what has happened historically
Forecast long-term seasonal cycles
Statistical inference is described as the process of doing what?
Cleaning raw data for exploratory plots
Designing data pipelines for storage
Drawing conclusions about a population from a sample
Building user interfaces for dashboards
In this material, how is a population defined?
A collection of unrelated experimental trials
A random subset of observations collected
The entire set sharing a common characteristic
Only individuals selected for study groups
Which example best matches the definition of a population provided?
Fifty voters chosen for a survey
All voters in a country
Students in a single classroom
A handful of defective products
Which statement correctly matches a population parameter to its description?
Population mean μ: the fraction with a trait
Population variance σ²: the average value overall
Population proportion p: the fraction with a characteristic
Population proportion p: variability within observations
A company wants a single value summarizing average output across all units produced. Which parameter fits this need?
Population variance σ² of units
Sample range of units
Population mean μ of units
Population proportion p of units
Which parameter would quantify how spread out measurements are across the entire population?
Population mean μ capturing central tendency
Population variance σ² capturing variability
Sample median capturing midpoints
Population proportion p capturing totals
A district estimates the share of students meeting a standard across all enrolled students. Which population parameter are they estimating?
Population mean μ representing average
Sample size n representing count
Population proportion p representing fraction
Population variance σ² representing spread
Which statement best defines a sample in data science?
The entire population measured exhaustively
A non-numeric summary of observations
A subset of the population used for analysis
A prediction generated by a model
Why is sampling often necessary in practice?
Collecting full population data is impractical
It guarantees zero sampling error
It always removes all types of bias
It replaces the need for measurement
Which example illustrates a sample?
Every citizen counted in a full census
All students enrolled across universities
All registered voters in a national database
1,000 voters selected from the voting population
In random sampling, what is the key property?
Dividing data into geographic clusters
Choosing units at fixed time intervals
Selection by researcher convenience only
Equal chance for every population member
Stratified sampling is most appropriate when the population has what feature?
Observations arriving in time order
Subgroups with shared characteristics
Perfectly identical individuals
Only one homogeneous category
Which procedure best describes systematic sampling?
Randomly selecting entire geographic regions
Choosing the nearest available participants
Balancing subgroups by proportional quotas
Selecting at regular intervals from a random list
Cluster sampling differs from stratified sampling primarily because cluster sampling involves
Randomly selecting entire clusters
Selecting only easily accessible units
Choosing individuals at fixed intervals
Sampling equally from each stratum
Which approach is most vulnerable to selection bias by design?
Convenience sampling from accessible groups
Random sampling across the full population
Stratified sampling across key subgroups
Systematic sampling from a random list
You have a population split into urban and rural regions with different sizes. To ensure both regions are represented proportionally, which method is most suitable?
Stratified sampling with proportional allocation
Systematic sampling every 50th entry
Convenience sampling near your office only
Cluster sampling selecting two regions
In data analysis, regression analysis is primarily used for
Randomly choosing entire clusters for study
Assessing relationships and making predictions
Ensuring each unit has equal selection chance
Dividing a population into homogeneous strata
