I'm a data scientist in Hamburg, Germany. Before I went into industry, I obtained a physics PhD from KIT for deriving insights on the structure of matter from CERN particle collision data. I love working with great people, getting creative with data, using state-of-the-art technologies and building awesome products. Interested in working together or having a chat? Feel free to contact me.
In a wide range of subject areas, I have analyzed structured and unstructured data to extract actionable business insights. I love to craft stunning and clever visualizations that illustrate surprising results.
I'm strongly convinced that machine learning models should not go to waste in Jupyter Notebooks. Using my software engineering skills, I've built and deployed AI services which create real business value.
I enjoy public speaking, writing professional articles, sharing my knowledge and discussing diverse topics. Thanks to my training and experience in science communication, I'm able to present complex results to a non-technical audience.
Medium's Towards Data Science is a great place to share wisdom. Here you'll find my articles on data science experiences and best practices.
Discover the structure of Wikipedia by flying around like you're in a spaceship. Based on public page link data and free graph software.
Occasionally, I create visualizations of public data, e.g. maps, traffic data or election results. This includes interactive websites for e.g. town names or carsharing prices.
Dataviz Instagram Town name suffix maps Hamburg carsharing price comparison
A dashboard to play around with and observe the effects of class imbalance or model strength on evaluation metrics. This project made it into the official Voila gallery.
I maintain a collection of articles which I've found helpful in my professional development, especially in my data science journey. Feel free to contribute. In addition, I've compiled a list of data science aphorisms on twitter.
I'm hosting a number of smaller projects on GitHub. This includes e.g. cookiecutter templates, bashrc templates, or minimal examples for creating machine learning services. Also, I've created the mplcyberpunk Python package to create TRON-style data visualizations. Feel free to have a look around.
To remind us humans about all the subconscious flaws in our reasoning, I've created "Cognitively Biased", a Twitter bot that tweets one entry from Wikipedia's list of cognitive biases every day.
I've built several websites to help people create more aesthetically pleasing graphs: The Matplotlib Style Configurator to interactively explore the effects of different parameter changes, the Matplotlib Style Poll to vote for your favorite style and discover new ones, and the interactive Matplotlib colormap generator.
An interactive online tool to embed stock price chart (for various companies) as a mountain range silhouette in a photo. The screenshot shows 10 years of Apple.
In my PhD thesis, I've analyzed proton collisions at CERN's Large Hadron Collider to derive insights on the structure of matter. At the same time, I've co-written the ARTUS framework for data analysis in high-energy physics. Its architecture and design principles are described in a separate paper.
Apart from data and technology, my hobbies include photography and literary writing.