AD-404 Data Science - Dec 2024 Question Paper

Under each question, How to answer lists the points an answer should cover, outlined by CampusPrep from the syllabus. Check the details against your textbook.

1. 8 Marks
   aWhat is Data Science? Explain the difference between structured and unstructured data.
   How to answer

   • Define Data Science as interdisciplinary field combining statistics, computing and domain knowledge
   • Define structured data with examples and schema
   • Define unstructured data with examples
   • Compare on format, storage, processing and analysis in table
2. 6 Marks
   bDiscuss about exploratory data analysis.
   How to answer

   • Define exploratory data analysis (EDA) and its objectives
   • List steps: data collection, cleaning, visualization, summary statistics
   • Mention tools and plots used
   • Explain role in discovering patterns and hypotheses
3. 7 Marks
   aWrite a brief note on importance of unstructured data.
   How to answer

   • Define unstructured data and its volume
   • Explain sources: text, images, video, social media
   • Discuss business value and insights
   • Note challenges in storage and analysis
4. 7 Marks
   bWhat is data visualization? Discuss feature map visualization technique.
   How to answer

   • Define data visualization and its purpose
   • Explain feature map visualization concept
   • Describe technique steps and interpretation
   • Give example use case
5. 7 Marks
   aExplain the concept of logistic regression.
   How to answer

   • Define logistic regression for classification
   • Explain sigmoid function and probability output
   • Describe cost function and parameter estimation
   • Mention applications and thresholding
6. 7 Marks
   bDiscuss in detail about losso regression.
   How to answer

   • Define lasso regression and L1 regularization
   • Explain penalty term and shrinkage to zero
   • Discuss feature selection property
   • Compare with ridge regression
7. 7 Marks
   aGive an overview of Gradient Bootstrap.
   How to answer

   • Define Gradient Boosting ensemble concept
   • Explain sequential weak learners and residual correction
   • Outline algorithm steps and loss optimization
   • Mention applications and advantages
8. 7 Marks
   bExplain the procedure to create scatter plots using Python.
   How to answer

   • List prerequisites: Python, matplotlib/pyplot, data
   • Give steps: import libraries, prepare data, plt.scatter, customize
   • Show sample code snippet
   • Explain display and saving plot
9. 7 Marks
   aExplain the major issues and challenges in Business Intelligence.
   How to answer

   • Define Business Intelligence context
   • Discuss data quality, integration and scalability issues
   • Explain cost, security and skill challenges
   • Suggest impact on decision making
10. 7 Marks
    bExplain the role of next-generation data scientists.
    How to answer

    • Define next-generation data scientist profile
    • Explain roles in AI, big data and automation
    • Discuss business collaboration and ethics
    • Mention required skills and tools
11. 8 Marks
    aWhat are the methods to evaluate Quantitative data? Explain.
    How to answer

    • Define quantitative data and evaluation need
    • Explain descriptive and inferential methods
    • Discuss visualization and statistical measures
    • Give examples of evaluation techniques
12. 6 Marks
    bList and explain the various charts in Excel.
    How to answer

    • List Excel chart types: column, line, pie, bar, scatter etc.
    • Explain purpose of each chart type
    • Describe when to use which chart
    • Give example data for charts
13. 8 Marks
    aExplain the following data analysis tools.

    1. i)SUMIFS
    2. ii)SUMPRODUCT
    How to answer

    • Define SUMIFS syntax and multi-criteria summing
    • Define SUMPRODUCT syntax and array multiplication
    • Give example formulas for each
    • Compare use cases
14. 6 Marks
    bWhat is over-fitting and under-fitting concept? Discuss.
    How to answer

    • Define overfitting with high variance symptoms
    • Define underfitting with high bias symptoms
    • Explain causes and detection via curves
    • Discuss prevention: regularization, cross-validation
15. 5 Marks
    aExplain the following in detail: Reinforcing human biases
    How to answer

    • Define human bias in data and algorithms
    • Explain how models amplify bias
    • Give examples of biased outcomes
    • Discuss mitigation strategies
16. 5 Marks
    bExplain the following in detail: Modern Business Intelligence
    How to answer

    • Define Modern Business Intelligence
    • Explain self-service, cloud and real-time features
    • Discuss components and tools
    • Mention benefits over traditional BI
17. 4 Marks
    cExplain the following in detail: Bagging and Boosting
    How to answer

    • Define Bagging with bootstrap sampling
    • Define Boosting with sequential weighting
    • Compare working, variance vs bias reduction
    • Give examples: Random Forest, AdaBoost