MCSL-065 IGNOU Guess Paper 2026-27

MCSL-065 (Data Science Lab) Term-End Exam (TEE) Guess Paper (Digital PDF)

This structured guess paper is designed to align with the official IGNOU curriculum for MCSL-065 (Data Science Lab) under the M.Sc. (Data Science and Analytics) program. It includes chapter-wise question weightage, solved previous year patterns (2018–2023), and 3-hour exam time management tips. Focus areas are derived from 3–5 core syllabus blocks with practical emphasis.

Core Syllabus Blocks Covered

• Unit 1: Data Preprocessing and Feature Engineering
  • Hands-on coding in Python (Pandas, NumPy) for data cleaning, normalization, and outlier detection.
  • Weightage: 20–25% of TEE marks; expect 2–3 coding questions (10–15 marks) and 1 theoretical question (5 marks).
  • Common mistakes: Incorrect handling of missing values or misapplication of scaling techniques.
• Unit 2: Machine Learning Model Deployment
  • Deployment of models using Flask/Django APIs or cloud platforms (AWS/GCP basics).
  • Weightage: 25–30% of TEE marks; focus on 1 practical question (20 marks) and 1 short-answer question (5 marks).
  • Previous year trends: 2022 Dec session had a 15-mark question on deploying a Random Forest model via Flask.
• Unit 3: Data Visualization and Storytelling
  • Advanced visualization using Matplotlib/Seaborn/Plotly for insights (e.g., interactive dashboards).
  • Weightage: 15–20% of TEE marks; 1–2 coding questions (10–12 marks) and 1 conceptual question (5 marks).
  • Tip: Always include 1–2 visualizations in your answers to score partial marks.
• Unit 4: Big Data Tools (Hadoop/Spark)
  • Basic Spark operations (RDDs, DataFrames) and Hadoop configuration (HDFS).
  • Weightage: 10–15% of TEE marks; expect 1 short-answer question (5 marks) and 1 practical (10 marks).
  • Note: Spark questions often require pyspark code snippets for full marks.
• Unit 5: Ethical and Legal Aspects of Data Science
  • GDPR, bias mitigation, and explainable AI (XAI) principles in code.
  • Weightage: 10% of TEE marks; 1 essay-type question (10 marks) or 2 short answers (5 marks each).
  • Frequent keywords: fairness, transparency, privacy-preserving techniques.

3-Hour Exam Time Management Tips

• First 30 minutes: Skim all questions, allocate time per section (e.g., 45 mins for coding, 30 mins for theory).
• Coding questions: Start with the highest-weightage topic (e.g., Unit 2: deployment) first.
• Theory questions: Use bullet points for Unit 5 (ethics) answers to save time.
• Last 15 minutes: Cross-verify outputs for coding questions (e.g., check Spark DataFrame schema).

Common FAQs

• Q: Are calculators allowed in the exam?

  No. Use Python for numerical computations during the exam (pre-loaded notebooks may be provided).

• Q: How to score in practical questions?

  Include input/output samples, comments in code, and 1–2 visualizations (e.g., Matplotlib plots) for full marks.

Sample Question Patterns (Based on Previous Years)

• June 2023: 20 marks on deploying a logistic regression model via Flask API + 10 marks on bias detection in a dataset.
• Dec 2022: 15 marks on Spark RDD transformations + 10 marks on GDPR-compliant data preprocessing.
• June 2021: 25 marks on end-to-end data pipeline (Pandas Scikit-learn Flask deployment).

Key Resources for Revision

• IGNOU Study Material (Units 1–5), Lab Manual (2023 edition).
• Kaggle notebooks for Unit 2 (deployment) and Unit 3 (visualization).
• Previous year solved papers (available on IGNOU’s official portal).