Gábor’s AI Courses
Gábor Békés · Central European University
Gábor’s AI Courses
Two courses on doing data analysis and research with AI, and the references and case studies behind them. All open, all free to use for teaching and learning.
Course · eight sessions
For students who already know data analysis or econometrics. Five weeks on setup, from raw data to report, wrangling and debugging, econometrics and text as data. Then a three-session capstone on manager changes in football, with web scraping, LLM APIs and difference-in-differences.
Mini course · four parts
For social scientists who have used AI as a chatbot, to polish a text or to search. We set up an AI agent, put it to work on a Word draft, a pile of readings and a small dataset, learn how to stay in charge, and watch it write a paper in 50 minutes.
Reference
Pages to come back to during and after the courses: a glossary of LLM terms, which AI model to use, setting up AI tools, working with APIs, and designing larger projects.
Data and code
Six case studies with data and code, used across the courses: the World Values Survey, Austrian hotels, football manager interviews, US earnings, employee commits, and common support in R.
Which course is for me?
Data Analysis with AI assumes a course in econometrics or data analysis and some coding in Python or R. It goes all the way to scraping, LLM APIs and modern causal econometrics.
The friendly introduction assumes neither. You give instructions in plain language, you use one tool, and you work on material from your own field. If you have never used an AI agent, it is a good place to start either way.
Rights and acknowledgement
You can use it to teach and learn freely
Attribution: Békés, Gábor: “Data Analysis with AI: a comprehensive course”, available at gabors-data-analysis.com/ai-course/, v2.2. 2026-05-01.
You can fork it from the Github Repo. github.com/gabors-data-analysis/da-w-ai/
License: CC BY-NC-SA 4.0 – share, attribute, non-commercial (contact me for corporate gigs)
Textbook Please check out the textbook behind all this, buy it if you can. If interested teaching contact the Cambridge UP or me.
Thanks
Thanks: Developed mostly by me, Gábor Békés Thanks a million to the two wonderful human RAs, Ms Zsuzsanna Vadle and Mr Kenneth Colombe, both Phd students. Also thanks to Adam Víg, long term collaborator now at Google. Thanks to Claude and ChatGPT to craft pages, improve consistency, create the simulated dataset. They helped create the slideshows and educated me on a bunch of topics like reinforcement learning or NLP. This is a beautiful example of collaboration with great young people while heavily benefiting from advanced AI. Thanks for Quarto – it was all drafted and written in Quarto and Rstudio by Posit. Plus all the love from Github.
Thanks for CEU’s teaching grant that allowed me pay people and AI.
Questions and suggestions
This material is based my course at CEU in Vienna, Austria. Here is the Github repo
If you have questions or suggestions or interested to learn more, just fill in this form.