Welcome to a 30-day, project-based sprint designed to simulate the complete lifecycle of a Product Analyst. You won't just learn isolated skills; you'll own a feature, from initial discovery in raw data to a final strategic recommendation in a Quarterly Business Review (QBR).
This is not a tutorial. It's a simulator. By the end, you will have a portfolio-ready project that demonstrates technical depth, business acumen, and strategic thinking.
Over 30 days, you will build a robust, end-to-end analytical skillset:
- Technical Foundations: Master advanced SQL for user behavior analysis, funnel creation, and cohort analysis in a realistic data environment (DuckDB).
- Experimentation & Causal Inference: Design a rigorous A/B test, perform power analysis, and implement a quasi-experimental backup (Difference-in-Differences) to measure true causal impact.
- Diagnostic & Monitoring: Learn to monitor a feature launch, diagnose bugs with precision, and communicate findings effectively under pressure.
- Predictive Analytics: Build a simple, interpretable machine learning model to identify high-value users and inform product strategy.
- Stakeholder Communication & Strategy: Practice distilling complex data into concise memos, compelling visualizations, and an executive-level presentation.
- Product & Business Acumen: Develop a deep understanding of metrics like LTV, cannibalization, and engagement loops, and use them to make data-driven product decisions.
You are a Product Analyst at a fast-growing social media company. The product team has a hunch that users want a private space to jot down thoughts, inspired by qualitative feedback. Your mission is to use data to validate this idea, measure its impact, and determine its future.
This project is split into two key parts: your local coding environment and the online curriculum.
This is where you will complete your daily challenges.
Setup (Required):
- Install Docker Desktop. This is the standard for creating reproducible data science environments.
- Clone this repository.
- From the project's root directory, run the command:
docker-compose up --build
- Open your web browser and navigate to http://localhost:8888. You will see the JupyterLab interface.
Directory Structure:
/notebooks: Contains the Jupyter notebooks for each day's challenge. This is where you'll work./data: Holds all raw datasets (.parquet,.csv)./src: A place for any reusable Python functions you write./solutions: Contains the completed solution notebooks for your reference.
The full 30-day syllabus, with detailed explanations and context, is deployed as a searchable website using mdBook. This is your primary reference.
➡️ Access the Live Masterclass Curriculum Here (Note: You must update this link after deploying your own version via GitHub Pages.)
Building the Book Locally: The book is generated from the project's markdown files. To build and preview it locally:
- Run the build script. This prepares the content for the book.
./scripts/build_book.sh
- Serve the book.
mdbook serve book-src
- Open your browser to
http://localhost:3000.
Deployment:
The included GitHub Actions workflow will automatically build and deploy the book to GitHub Pages on every push to the main branch.