Module 1 – Introduction to Data Science (8 hours)
- What is Data Science? How it differs from ML, AI, and Analytics
- Latest trends in 2025: Generative AI in analytics, Augmented Analytics, AI-driven BI tools
- Data Science lifecycle: Data → Insights → Action → Deployment
- Environment setup: Python, Jupyter Notebook, GitHub, Kaggle
- Python basics for DS: Data types, loops, functions, libraries overview (NumPy, Pandas, Matplotlib, Seaborn)
Hands-on:
- • Load datasets from CSV & APIs
- • Generate descriptive statistics & basic plots
Module 2 – Data Wrangling & Exploration (10 hours)
- Handling missing values & duplicates
- Outlier detection & treatment
- Data transformations (log, binning, encoding, scaling)
- Merging, joining, and reshaping datasets
- Exploratory Data Analysis (EDA) best practices
- Latest trends: Automated EDA tools (y-data-profiling, Pandas AI)
Hands-on:
- • Perform complete EDA on a Kaggle dataset
- • Create interactive dashboards with Plotly
Module 3 – Statistics & Probability for Data Science (10 hours)
- Descriptive statistics (mean, median, mode, variance, std dev)
- Probability basics & distributions (Normal, Poisson, Binomial)
- Inferential statistics: Hypothesis testing, t-test, chi-square test
- Correlation & covariance
- Latest trends: Bayesian statistics in modern analytics
Hands-on:
- • Hypothesis testing on A/B testing dataset
- • Probability-based predictions
Module 4 – Machine Learning for Data Science (14 hours)
- Supervised vs Unsupervised learning
- Regression models (Linear, Lasso, Ridge)
- Classification models (Logistic, Decision Tree, Random Forest, XG Boost)
- Clustering (K-means, DBSCAN)
- Model evaluation metrics (MAE, RMSE, Accuracy, F1-score, ROC-AUC)
- Latest trends: AutoML (H2O.ai, Auto-sklearn), Explainable AI
Hands-on:
- • Build a predictive model for a business problem
- • Evaluate models with multiple metrics
Module 5 – Advanced Data Science Techniques (12 hours)
- Feature engineering & selection techniques
- Time series forecasting (ARIMA, Prophet, LSTM basics)
- Natural Language Processing basics (tokenization, embeddings, sentiment analysis)
- Big Data & Cloud integration overview (Spark, Google Big Query)
- Latest trends: Data Ops, ML Ops, Data-centric AI
Hands-on:
- • Forecast sales for a retail store
- • Perform sentiment analysis on social media data
Module 6 – Capstone Project & Deployment (18 hours)
Project Theme:
- "Data-Driven Decision Making" – Students select a domain (finance, healthcare, marketing, etc.) to:
- 1. Collect or source a dataset (from Kaggle, APIs, or web scraping)
- 2. Perform full EDA and preprocessing
- 3. Apply ML models and evaluate results
- 4. Create visualizations & actionable insights
- 5. Deploy findings via a dashboard or app (Streamlit, Power BI, or Tableau)
Examples:
- • Customer segmentation & recommendation system
- • Predictive sales dashboard
- • Real-time sentiment analysis tool for brand monitoring
Final Deliverables:
- • Code + Report + Dashboard/App
- • Presentation & Q&A session
Assessment & Certification
- • Weekly Quizzes: 20%
- • Assignments: 30%
- • Capstone Project: 50%
- • Minimum 60% score for certification
Reviews
There are no reviews yet.