Course Wiki

Stock Markets Analytics Zoomcamp

DataTalks.Club's free stock market analytics course run with PythonInvest: financial data sources, pandas analysis, time-series modeling, trading strategy simulation, and automation.

Stock Markets Analytics Zoomcamp is DataTalks.Club’s free course on data-driven stock market analysis, run together with PythonInvest. It moves from data sources to deployed analysis: downloading financial data through APIs, analyzing it in pandas, modeling time series, simulating trading strategies on top of predictions, and automating the whole loop.

All materials are open source in the course repository, with videos on the PythonInvest YouTube channel and a course FAQ. The course can be taken fully self-paced; the most recent live cohort started May 19, 2025.

Curriculum

All modules, each with its lesson-level notes:

• Module 1: Introduction and Data Sources
• Module 2: Working with the Data in Pandas
• Module 3: Modeling for Time Series
• Module 4: Trading Strategy and Simulation

• Module 5: Deployment and Automation

• Module 1: Introduction and Data Sources — data-driven decision making, the landscape of personal investments, risk and reward, Colab setup, and choosing market data APIs.
• Module 2: Working with the Data in Pandas — pandas, NumPy, Matplotlib, Seaborn, and Plotly Express; data types and cleaning; feature generation including technical indicators with the Ta-Lib library and future-growth targets.
• Module 3: Modeling for Time Series — hypothesis framing, time-series decomposition into trend, seasonality, and remainder, regression (linear regression), and binary classification for growth direction.
• Module 4: Trading Strategy and Simulation — trading strategy design: fees, risk management, combining predictions, and market entry timing; strategy examples from single-stock long-term investment to diversified portfolios, market-neutral long-short, event-driven mean reversion, and pairs trading; strategy simulation and backtesting.
• Module 5: Deployment and Automation — moving from notebooks to Python files, persistent storage with files and SQLite, scheduling with cron and workflow tools such as Airflow, and systematic prediction-and-trade execution (deployment automation).
• Project — two weeks of project work followed by a peer-review week.

Looking for a specific concept? The Concept Glossary links every concept this course teaches to the exact modules and lessons that cover it.

Who it is for

The course suits learners who want practical, data-first exposure to financial markets: analysts and developers building an analytical toolset around stocks, and data professionals curious about trading applications of ML. The prerequisite bar is basic Python and comfort with notebooks; deep finance or ML background is not assumed.