Hello! I'm Riccardo.
I am a research engineer working on the Skrub library at Inria Saclay.
I am mostly interested in tabular data cleaning and processing, information retrieval, feature selection, and how to optimize machine learning tasks around that. I have also worked with word and graph embeddings, graph neural networks, and their application to data curation tasks.
I work mostly with Python and its data science libraries (Polars, Pandas, scikit-learn, skrub, numpy, matplotlib, seaborn...).
My main projects are:
If you want to reach out, you may contact me on Linkedin or send me an email to riccardo[dot]cappuzzo[at]protonmail[dot]me.