Retrospective - Future Work
In Apr 2024 in the Netherlands I wrote the artcle “Future Job” (in Notion). Here I mentioned my wish-job/wish-life list with a 2 years outlook, and now the time has come.
Marco Di Francesco Portfolio
📊 Help extracting Meaning out of Data | 🇪🇺 EIT Data Science Msc | 🙋♂️ 2024 EIT Student Ambassador
Latest posts
Credit Card Switzerland - Cashback
Yeeee another let’s-optimize-the-small-cents rabbit hole. Credit card now.
Non Zürich?
Let’s explore the question: when applying to new positions, should I just apply to Zurich instead of all of Switzerland? It has been ~3 months since I started applying. This reflection comes because I got an interview from Basel a few days ago, and one of the first things I thought was “it’s way too close to the German border”. Here we go again with this mindset of diversification to slowly grind…
Gold Step Back
Gold step back: In may I got allured by gold returns in period 2000-2025 which have shown very similar returns and seemingly opposite trends. The thought of hedging against risk-adjusted returns was so fascinating that I allocated 12% of my 2025 end-of-year portfolio allocation.
Underwhelming Keyboard
Following the previous post 8 days ago: 2025-08-23-new-beautiful-keyboard
New Beautiful Keyboard
In Aug 2025, after 4 months in Corner I have a sudden will to have a beautiful keyboard in the office. I want it so that if someone approaches me they say: “wow, that’s really a beautiful keyboard”.
LightRiver — Master Thesis
Ported an Online Machine Learning model from Python to Rust, achieving a 97% reduction in execution time and attaining a processing capability of 10,000 records per second for IoT devices. Optimized memory usage to a minimal 20MB, facilitating deployment on robots with stringent memory limits and resulting in a 55% enhancement in positioning accuracy. Specialized implementation of Mondrian…
NYCTaxis
Analyzed taxi tipping behavior using Apache Spark to process large-scale datasets (67 GB of Yellow Taxi trip) to assess the impact of ride area, time, distance, and traffic on tipping. Employed Spark for data aggregation and analysis, generating insights into spatial and temporal patterns of taxi rides and their correlation with tipping trends. Visualized findings using Python libraries…
MT-SMAC
Implemented improvements to a multi-target Hyperparameter Optimization model, extending and enhancing the work of a PhD project. The project, known as MT-SMAC, focuses on the Sequential Model-based Algorithm Configuration (SMAC) for optimizing highly parameterized algorithms. Conducted empirical analysis using the YAHPO gym for benchmarking, providing insights into the efficiency and robustness of…
CourseMatch
Developed a Course Recommender System in a team of 3 students using a Transformer based Large Language Model (LLM). Utilized the BERT model from the HuggingFace library to generate embeddings for both the query and the corpus. Conducted comprehensive experiments on a custom-built database and evaluated the models using various similarity techniques. Recognized as the Best Project in the 2023…