AI system predicts football outcomes using tactical profiles, outperforming traditional methods

Researchers have developed Sim2Win, a novel framework for predicting football match outcomes and profiling team tactics without relying on team names or identities. This system utilizes event-based data to construct tactical profiles and identify playstyles, demonstrating strong generalization capabilities to unseen teams. Evaluations show Sim2Win outperforms traditional methods like ELO and Pi-Rating, with CatBoost achieving the highest accuracy among the evaluated models. AI

IMPACT This system could enhance sports analytics by providing more objective and generalizable tactical insights, potentially influencing team strategies and scouting.

RANK_REASON The cluster contains a research paper detailing a new AI system for sports analytics. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• CatBoost
• DagsHub
• Elo
• Gap
• Hugging Face
• k-means clustering
• Pi-Rating
• Sim2Win
• StatsBomb

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →