Customer Churn Prediction
An end-to-end model, from raw data to a deployed API.
- Feature engineering
- Model tuning and SHAP explanations
- MLflow and FastAPI
Data Science · Intermediate
Data Science
Apply statistics and Python to explore data and build predictive models.
- Python
- Statistics
- Pandas
- Scikit-learn
- PyTorch
- LLMs and RAG
- MLflow
About this course
Apply statistics and Python to real problems, build and evaluate machine learning models, and learn how data science now works alongside LLMs and MLOps.
Who this is for
- Analysts moving into data science
- Developers adding machine learning
- Graduates with programming and statistics basics
What you will be able to do
- Explore data and test hypotheses
- Build, tune and evaluate machine learning models
- Explain model decisions to business teams
- Track experiments and deploy a model as an API
- Build a simple LLM and RAG application
Prerequisites: Basic programming and statistics.
8-week curriculum
- 8
- Learning units
- 40
- Topics covered
- 2
- Projects
- 10
- Tools
Week 1
Python for Data Science
- NumPy and Pandas
- Data cleaning
- Visualization
- Exploratory data analysis
- Notebooks and Git
Assignment
Complete an exploratory analysis of a public dataset.
Week 2
Statistics and Experimentation
- Probability and distributions
- Sampling and confidence intervals
- Hypothesis testing
- A/B testing
- Common statistical mistakes
Assignment
Design and analyse an A/B test.
Week 3
SQL and Feature Engineering
- SQL for data science
- Window functions
- Encoding and scaling
- Handling missing data
- Avoiding data leakage
Assignment
Build a feature set from raw tables.
Week 4
Supervised Learning
- Linear and logistic regression
- Decision trees and random forests
- Gradient boosting with XGBoost
- Cross-validation
- Metrics: precision, recall, F1 and AUC
Assignment
Build a customer churn model.
Week 5
Unsupervised Learning and Interpretability
- Clustering
- Dimensionality reduction
- Hyperparameter tuning
- Explaining models with SHAP
- Fairness and bias
Assignment
Segment customers and explain your churn model.
Week 6
Deep Learning and NLP
- Neural network fundamentals with PyTorch
- Text processing
- Embeddings
- Transformers and Hugging Face
- When simple models are better
Assignment
Build a text classifier.
Week 7
LLMs, RAG and MLOps
- Working with LLM APIs
- Prompt engineering
- RAG with a vector database
- MLflow experiment tracking
- Serving a model with FastAPI and Docker
Assignment
Deploy your model and build a small RAG demo.
Week 8
Capstone and Interview Preparation
- End-to-end capstone
- Communicating results
- Statistics and ML interview questions
- Case study practice
- Portfolio and resume review
Assignment
Present your capstone and complete a mock interview.
Keep the full curriculum with you
Verify your email and download this course as a PDF.
Projects you will build
Document Q&A Assistant
A RAG application over a set of documents.
- Embeddings and vector search
- LLM integration
- Evaluating answer quality
These are training projects. Please describe them honestly as training work on your resume and in interviews.
Tools and technologies
- Python
- Pandas
- Scikit-learn
- XGBoost
- PyTorch
- Hugging Face
- SQL
- MLflow
- FastAPI
- Docker
Career support
- Resume tailored to your target role
- LinkedIn, Naukri and Indeed profile guidance
- Technical and HR mock interviews, with feedback
- Help explaining your projects clearly
MYP does not guarantee a job or interviews.
Need More Information? Connect with Our Course Expert.
Ask about the course, fees, duration or which path suits your background.
₹40,000