Esplorazione
Context & ObjectiveClarifying the problem, the decision to improve, the users involved and the expected outcome.
Data & Analytics
Patrones Lab is a data analytics lab focused on real-world, everyday phenomena.
It brings together independent projects built with public data, with an emphasis on finding patterns, explaining behavior and communicating insights with context.
The goal is to ask better questions, prepare reliable data, build reproducible analyses and turn results into clear visual outputs.
Clarifying the problem, the decision to improve, the users involved and the expected outcome.
Mapping available data sources, including their origin, refresh cadence, reliability and main limitations.
Structuring, cleaning and combining data into a consistent analytical dataset ready for analysis.
Building the analysis, model or dashboard required to address the defined objective.
Reviewing the coherence, stability and business relevance of the results before delivery.
Documenting the final output, automating recurring workflows and using feedback to guide future improvements.
A selection of applied projects built with public data, documented methodology and visual outputs. Use the filters to explore by discipline, tool or deliverable type.
Analysis of air traffic in Spain using public AENA data, focused on volume, airport-level patterns and differences across traffic categories.
Exploratory analysis of Airbnb listings in London, focused on pricing, property categories, reviews and spatial patterns.
Analysis of reported Chicago taxi trips to study duration, demand, geospatial distribution and operational patterns.
Supervised classification of listings as relatively expensive or inexpensive within each accommodation type.
Interactive Looker Studio dashboard for exploring Chicago taxi trips, operational indicators, hourly patterns and pickup-dropoff routes.
Logistic regression model that estimates the probability of each shot becoming a goal using public StatsBomb data, match-level validation and application to the Qatar 2022 World Cup.
Open project
Probabilistic Expected Threat model in soccer using public StatsBomb data. It estimates the probability of a goal in the next 5 actions.
✅ published
Unsupervised K-means clustering applied to credit card fraud detection.
✅ published
Supervised logistic regression model for credit card fraud detection.
✅ published
Unsupervised DBSCAN clustering to detect potential credit card fraud patterns.
Open project
Analysis of 2022 World Cup statistics using public StatsBomb data, focused on summarizing individual performances and comparing players through percentile radar charts.
Geospatial analysis of Chicago taxi trips, focused on identifying activity hotspots, urban routes and the territorial concentration of demand.

Analysis of Spotify Charts music rankings using public data on songs, artists, albums and markets, focused on exploring streams, chart presence, temporal leadership and territorial distribution through an interactive Power BI dashboard.
✅ published
Interactive Power BI report for analyzing supplier spend, monthly trends, category distribution, savings and geographic distribution.
Simulation of one million 2026 World Cup scenarios using Elo ratings to estimate the probability of reaching the semifinals, playing the final and becoming champion.
For professional opportunities, analytics collaboration or BI, machine learning and dashboard projects.
Send me a message and I’ll get back to you shortly.