Python (scrapy, asyncIO), Apache Airflow, GCP (Storage Bucket, Functions, BigQuery, VM), dbt, Terraform, Docker

⛏⚽ Scrape soccer data from Club Elo, ESPN, FBref, FiveThirtyEight, Football-Data.co.uk, FotMob, Sofascore, SoFIFA, Understat and WhoScored.

Project for submission to SSAC2025

⚽️ Extract, prepare and publish Transfermarkt datasets.

Convert soccer event stream data to SPADL and value player actions using VAEP or xT

Ferramenta que analisa jogos de futebol ao vivo e preve a ocorrência do primeiro gol na partida. Para isso, foi coletado dados de jogos diários ao vivo por um período de mais de um ano e treinado modelos de aprendizagem de máquina.

Streamlit app to present Football Player Evaluation

This project is a used to gather data from Kickbase API endpoint and automate various interactions. The data is visualized in a GUI.

AIFootballPredictions is an ML-based system to predict if a football match will have over 2.5 goals. Using historical data from top European leagues (Serie A, EPL, Bundesliga, La Liga, Ligue 1), it employs advanced feature engineering and model training techniques to provide accurate predictions. Perfect for sports analytics enthusiasts.

All matches of English Professional Soccer League. From 1993 up to date

Weekly football app for friends with no skill in the game 😂

EA FC 25 Automated SBC Solving using Integer Programming ⚽

This project visualizes the pass network from Barcelona's 2020 match against Valladolid. It processes match event data, focusing on successful passes before the first substitution. Players are represented as nodes, with arrows indicating passes. The visualization highlights team interactions and passing dynamics on the field.

Detect football players in videos using YOLOv5 for training and YOLOv8 for inference. The dataset is sourced from Roboflow and includes 663 annotated images. The project involves pre-processing, augmentation, and model training for accurate player detection.

football-analytics

Management assistance for Kickbase Bundesliga Manager

Rest API built in Express to obtain players data from the 2013-2014 European Leagues

Generalized-VDEP. This metric was presented in MathSports 2023.

The unravelsports package aims to aid researchers, analysts and enthusiasts by providing intermediary steps in the complex process of turning raw sports data into meaningful information and actionable insights.