📊 Algorithm-Driven · 8 PYQ Papers Analysed

Score Full Marks
in Data Science

21CSC201J · SRM IST · Semester 3
Foundation of Data Science — Complete Smart Study Hub

5
Units Covered
8
PYQs Analysed
60+
Key Concepts
15
Must-Know Topics
View PYQ Analysis → Start Studying
↓ scroll to explore
DRIVE RESOURCES

📚 Notes & Presentations

Unit-wise lecture notes, PPTs & study material synced from Google Drive

⏳
Connecting to Google Drive…
🔥 Units 2 & 3 = 50% of marks.  Statistics & Probability and Data Wrangling appear in every paper. Measures of central tendency, Bayes' theorem, Linear Regression, and Pandas operations are guaranteed mark-scorers. Master these first!
📈 Data-Driven Analysis

PYQ Pareto Analysis

Based on 8 exam papers. Master the 20% of topics that yield 80% of marks.

🔥 HOT
Unit 1
Introduction to Data Science
18%
14 / 75 marks
🔥 HOT
Unit 2
Statistics & Probability
26%
20 / 75 marks
Unit 3
Data Wrangling & Visualisation
24%
18 / 75 marks
Unit 4
Machine Learning Fundamentals
20%
15 / 75 marks
Unit 5
Big Data & Tools
12%
8 / 75 marks

🏆 Top Topics — The Pareto List

Mastering only these topics lets you score 55–65 out of 75

🌡️ Topic Frequency Heatmap

📚 Complete Study Guide

Unit-by-Unit Study Guide

Clear concepts, algorithms, worked examples, and common mistakes for every unit.

⚡ Quick Reference

Data Science Formula & Concept Cheat Sheet

All exam-critical formulas, algorithms, and statistical equations in one place.

🎯 Exam Strategy

Guaranteed Marks Plan

How to approach each part of the Foundation of Data Science exam for maximum marks.

Part A
25 MCQs × 1 = 25 marks
Target: 20–23 / 25
  • Types of data — structured, unstructured, semi-structured 8/8
  • Mean, Median, Mode — formula & when to use which 8/8
  • Bayes' Theorem — formula & conditional probability 8/8
  • Pandas — DataFrame operations, groupby, merge 7/8
  • Linear Regression — equation, least squares, R² 7/8
  • Confusion Matrix — TP, FP, TN, FN, Precision, Recall, F1 7/8
  • Normal Distribution — 68-95-99.7 rule, Z-score 6/8
  • K-Means Clustering — steps and convergence 6/8
  • Hadoop ecosystem — HDFS, MapReduce, YARN 6/8
  • Data preprocessing — missing values, normalisation, encoding 5/8
Part B
5 Questions × 8 = 40 marks
Target: 32–40 / 40
QUnitExpected Topic
21U1Data Science lifecycle + roles (Data Scientist vs Analyst) 🔥
22U2Bayes' Theorem with numerical + Normal Distribution 🔥
23U3Pandas operations — describe, groupby, merge, handle missing values 🔥
24U4Linear Regression derivation OR Decision Tree with entropy calculation
25U5Hadoop MapReduce word count example OR Spark vs Hadoop comparison
Part C
1 Question × 10 = 10 marks
Target: 8–10 / 10

Choose 1 of 2 questions. Typical options:

Q.26
Complete ML pipeline: preprocessing → model → evaluation (with Confusion Matrix, Precision, Recall, F1) 🔥 OR Statistical analysis — hypothesis testing (t-test, chi-square) with numerical example
Q.27
K-Means clustering with worked numerical example + when to use K-Means vs hierarchical 🔥 OR Big Data — Hadoop architecture + MapReduce workflow with word count example
💡 Data Science Exam Secret: Always show your working for numerical questions (mean, variance, Bayes, regression). For algorithm questions, write the step-by-step pseudocode/procedure first, then apply to the example. Examiners give partial marks for correct steps even if the final answer is wrong. A labelled diagram of the ML pipeline always impresses!

🔮 Predicted Next Exam Topics

Based on recent patterns

✏️ Practice Zone

Solved Questions & MCQ Drill

The most-repeated solved questions from 8 years of PYQs, plus MCQ flashcards.

🃏 MCQ Flashcards — Active Recall Drill

Click A, B, C, or D to commit your answer. Get instant feedback. Track your score below.

✅ Correct: 0
❌ Wrong: 0
📊 Total: 0

✅ Final Revision Checklist

📜 Past Year Papers

Solved PYQs

Select a paper to view its full HTML solution.

✍️ Quick Scratchpad
⚡ Quick Formula Look-up
All Formulas
📋 Copied to clipboard!
✨ New: Live Compiler + AI Assistant