Double Master’s student in Data Science at the University of Padua and Universitat Politècnica de Catalunya, with a background in Statistics and Information Management and a strong focus on applied machine learning and experimental rigor.

• 🔭 I’m currently:

  • Maintaining and improving open-source ML implementations on GitHub, including methods such as Friedman's Regularized Discriminant Analysis.

• 🎓 Education:

  • Double Master Degree in Data Science – University of Padua & Universitat Politècnica de Catalunya (2024 – current).
  • BSc in Statistics and Information Management – University of Milan-Bicocca.

• 🧪 Some recent projects and research:

  • Benchmarked 20+ categorical encoders on 10+ tabular datasets in supervised learning, with a strong emphasis on reproducibility and rigorous evaluation.
  • Implemented distributed k-means (Lloyd’s algorithm) and a fair variant in PySpark, plus streaming frequency estimation with Count-Min Sketch vs Count Sketch.
  • Built NLP pipelines with Transformers, BERT, and RAG for tasks like text classification, fake-news detection, and domain-specific question answering.

• 💡 What I enjoy:

  • Turning messy, real-world data into clear insights and robust models, from implementation of ML algorithms to recommender systems and optimization.
  • Bridging theory and practice through open, reproducible experiments and clean, well-documented code.

• 📫 How to reach me:

  • Email: fez.cle@gmail.com
  • LinkedIn: linkedin.com/in/federicoclericii
  • GitHub: github.com/F3z11

Also working with: R, SQL, SAS, Apache Spark/PySpark, Jupyter, VS Code, Tableau, Git/GitHub.