Small data.
Strong noise.
Great insights.
Featured product
Barudion.com unlocks quantitative investing for everyone! Barudion offers model ETF portfolios backed by Bayesian statistics that identify outperforming markets (such as stocks, bonds, or commodities) and finds the optimal trade-off between diversification and capital concentration. Replicate our model portfolios in your own brokerage account and receive regular portfolio updates.
Interactive course
Investing is not a guessing game, and investment decisions should be made in a rational, data-driven manner. Our interactive online course “Invest with Code” will teach you basic as well as advanced methods used in quantitative investing via interactive Python code examples. We believe that programming offers an easy approach to math-heavy subjects, as code snippets can be interactively tested and fiddled with to build an intuitive understanding of the inner workings of even very complex mathematical models.
We tackle problems holistically.
Consulting
We support your team in tackling specific problems on probabilistic programming, optimization, risk mitigation, or complex systems in general. learn more ►
Education
We provide code-first, math-second courses with plenty hands-on experience and interactive lecture materials. learn more ►
Products
We provide software products for small-data problems and time series analysis in general, and for specific applications such as portfolio optimization and derivative markets. learn more ►
Latest from the journal.
Research notes, product updates, and practical examples from our work on probabilistic modeling, portfolio construction, and noisy data.
Fortezza Artifact Multi-Asset Growth Index: Recap After 3 Months
Three months after launch, our strategic certificate has faced a difficult macro environment marked by tariff volatility, an Iran-driven energy shock, and renewed regime uncertainty — while our adaptive allocation process has responded by de-risking, broadening diversification, and preserving optionality.
2025 Recap: One Year of Live Trading
A full-year live trading recap of Barudion's Basic and Pro portfolios in 2025, benchmarked against the S&P 500 (EUR total return), including allocation changes and simulation-vs-live performance.
Build your own AI: how to teach GPT to search the web and execute code
Large Language Models such as GPT-3, ChatGPT, Bing AI, and Google Bard have recently demonstrated stunning advances in conversational capabilities, text summary, translation, code creation and many other applications. Microsoft’s new AI-powered search assistant Bing showed how these capabilities can be further enhanced by allowing the AI agent to access conventional search engines and read web pages. In this post, we will take a closer look at the Python package langchain , which allows us to easily combine an LLM such as GPT-3 with other functionalities like web search, a Python interpreter, and a terminal session for code execution. With just 50 lines of code, you can create your own personalized AI agent that retrieves information from the internet, implements algorithms in Python, and runs code to solve tasks.