Data science is an interdisciplinary field that integrates domain expertise, computer science, and statistical methods to extract meaningful insights from data. 

Data analysis is important within specific Sciences, business, or engineering contexts. The ACM and IEEE's curriculum emphasizes:

• Foundational knowledge in programming, data structures, algorithms, and statistics.

• Practical applications of data management, machine learning, and data visualization.

• Ethical considerations in data privacy, security, and societal impacts.

• Contextual learning, where students apply data science skills to specific domains​

Reference    Syllabus    Concept Map

• Understanding Plots

• Some Problems

Unit 1: Introduction to Data Science (Week 1)

1. What is Data Science?

   • Multi-disciplinary nature (CS + Stats/ML + Domain)

   • Hypothesis-Driven vs. Data-Driven paradigms

   • Core mindset: Always ask questions

2. Types of Data

   • Structured vs. Unstructured

   • Quantitative vs. Categorical

   • Big Data and the 3Vs (Volume, Velocity, Variety)

3. Common Data Sources and Formats

   • CSV, JSON, XML, SQL dumps, APIs, Web scraping, etc.

Unit 2: Core Types of Data Science Problems (Week 1–2)

1. Classification Problems

2. Regression Problems

Unit 3: Probability & Statistics Foundation (Week 2–3)

1. Probability Overview

   • Experiments, Sample Space, Events

   • Probability rules, Random Variables, Expected Value

   • Independence, Conditional Probability, Bayes’ Theorem

   • Joint & Marginal Probability

   • PDF vs. CDF

2. Descriptive Statistics

   • Measures of Centrality (Mean, Geometric Mean, Median, Mode)

   • Measures of Variability (Variance, Standard Deviation)

   • Interpreting Variance

   • Correlation (Pearson & Spearman) – “Correlation ≠ Causation”

Unit 4: Classic Statistical Distributions (Week 3)

1. Binomial Distribution

2. Normal (Gaussian) Distribution & 68-95-99.7 rule

3. Poisson Distribution

4. Power-Law Distributions & Pareto Principle (80/20 rule)

Unit 5: Data Preprocessing Pipeline (Week 4–5)

1. Data Cleaning

   • Errors vs. Artifacts

   • Data Compatibility & Unit Conversion

   • Missing Value Imputation techniques

   • Outlier Detection

2. Feature Engineering

   • Continuous features: Scaling, Binning, Log transforms, Interactions, PCA

   • Categorical features: Label/Ordinal encoding, One-Hot, Hashing, Embeddings

3. Sampling Techniques

   • Inverse Transform Sampling

   • Monte Carlo methods

Unit 6: Modeling Fundamentals (Week 6)

1. Why we model: Prediction vs. Inference

2. Error components (Reducible vs. Irreducible)

3. Modeling Philosophies

   • Occam’s Razor

   • Bias-Variance Trade-off

   • No Free Lunch Theorem

   • Nate Silver style: Think probabilistically, update with new evidence, seek consensus

Unit 7: Modeling Taxonomy & Evaluation (Week 7)

1. Types of Models

   • Parametric vs. Non-parametric

   • Supervised vs. Unsupervised

   • Black-box vs. Interpretable

   • Deterministic vs. Stochastic

2. Evaluation Metrics

   • Classification: Accuracy, Precision, Recall, F1, ROC-AUC

   • Regression: MSE, RMSE, MAE, R²

3. Evaluation Environment

   • Train/Validation/Test splits

   • Cross-Validation (k-Fold, LOOCV)

   • Bootstrapping

   • Handling small datasets

Unit 8: Supervised Learning – Regression & Classification (Week 8–9)

1. Linear Regression

   • Ordinary Least Squares (closed-form & Gradient Descent)

   • Regularization (Lasso, Ridge)

   • Feature selection & dimensionality reduction

   • Evaluation (RSE, R², p-values)

2. Logistic Regression

   • Maximum Likelihood Estimation

   • Handling imbalanced & multi-class problems

Module 9: Instance-based & Clustering Methods (Week 10)

1. Distance Metrics (Euclidean, Manhattan, Cosine, KL, JS)

2. k-Nearest Neighbors (k-NN)

   • Algorithm & optimization (LSH, KD-Trees)

3. Clustering

   • K-Means (including choosing K)

   • Hierarchical Clustering & Dendrograms (Linkage types)

Unit 10: Tree-based & Ensemble Methods (Week 11)

1. Decision Trees (advantages & disadvantages)

2. Ensemble Techniques

   • Bagging & Random Forests

   • Boosting (concept)

3. Naive Bayes Classifier

4. Support Vector Machines (overview)

5. Principal Component Analysis (PCA)

Module 11: Deep Learning & Big Data Basics (Week 12)

1. Introduction to Deep Learning

   • Key architectures: DNN, CNN, RNN, GAN, Transfer Learning

   • Core concepts: Neurons, Activation functions, Backpropagation, Dropout, etc.

   • TensorFlow basics (Tensors, Variables)

2. Big Data & Hadoop Ecosystem (high-level)

   • HDFS, MapReduce, YARN

   • Hive, Pig, Spark, HBase, Kafka, Sqoop, Oozie

Unit 12: Supporting Tools & Concepts (Week 13–14)

1. Essential SQL

   • SELECT, WHERE, GROUP BY, JOINs, Subqueries

2. Python Data Structures

   • Lists, Tuples, Dictionaries, Sets

   • Collections (deque, Counter), heapq

3. Machine Learning Terminology Recap

   • Overfitting, Regularization, Hyperparameters, Cross-entropy, A/B testing, etc.

Final Week

• Capstone Project / Revision

• Recommended Resources & Further Learning Paths

• Programming Assignment { R/ Python ] From the Beginning of Semester - To be Submitted 

•  LAB Assignments Reference

•  Assignment Questions :- November /December

• Case Study

• Test - MCQ

• Sample Video Submitted: 👉 Priyanshi Soni  

Assignment Submission Link