Tagged articles
Sports Analytics
12 articles · Page 1 of 1
UIUC postdoctoral researcher Chen Xusi will join the Chinese University of Hong Kong as a tenure-track assistant professor in fall 2027, focusing on self-evolving language agents, LLM reasoning and alignment, lifelong learning, multimodal understanding, AI for science, and sports analytics.
AI for ScienceLLM AlignmentLifelong Learning
0 likes · 6 min read

The article examines conflicting claims about the Su Super League's popularity by defining three dimensions of "heat"—online attention, offline attendance, and commercial monetization—presenting data that shows a 16% rise in stadium crowds while online buzz naturally wanes, and explaining how weight choices drive the debate.
Chinese footballSIR modelSports Analytics
0 likes · 10 min read

The article explains how the Poisson distribution models football scores, demonstrates calculations for the Argentina‑France World Cup match, and reveals why its independence assumption and static nature let bookmakers out‑perform bettors using advanced bivariate and zero‑inflated Poisson models.
Poisson distributionSports Analyticsbivariate Poisson
0 likes · 13 min read

Goldman Sachs used an Elo‑rating system combined with Poisson‑regressed goal forecasts and a Monte Carlo tournament simulation to assign Spain a 26% chance of winning the 2026 World Cup, while also highlighting the model’s blind spots such as defense, injuries and coaching factors.
Elo ratingGoldman SachsMonte Carlo simulation
0 likes · 8 min read

A logistic‑regression model using net efficiency differential and recent momentum predicts the Thunder to win Game 7 with about an 87% probability (range 65‑96%), yet the Spurs retain roughly a 13% chance, hinging on factors like Victor Wembanyama’s scoring and Jalen Williams’s injury‑adjusted impact.
NBASports Analyticsgame 7 prediction
0 likes · 12 min read


AntTechJun 20, 2024 · Artificial Intelligence
During the 2024 European Championship, TuGraph engineers built an interactive system called “Smart Guess Football” that combines graph computing, graph neural networks, transformers and large language models to model player relationships and predict match outcomes, achieving up to 71% accuracy on limited test matches.
AIGraph Neural NetworkSports Analytics
0 likes · 7 min read

This article presents a statistical approach to forecasting football match results by calculating league-wide average goals, deriving offensive and defensive indices for each of the 20 teams, adjusting for home‑field advantage, and applying the Poisson distribution to estimate score probabilities.
Poisson distributionSports Analyticsfootball prediction
0 likes · 9 min read

This article explores how artificial intelligence techniques such as deep learning, object detection, multi‑object tracking, and coordinate projection are applied to football video analysis to automatically detect the ball and players, map their positions onto the field, and recognize key events like shots and goals.
AIComputer VisionObject Detection
0 likes · 16 min read

The study applies machine‑learning models—including logistic regression, SVM, random forest, deep neural networks and a DNN‑SVM ensemble—to 17‑dimensional team features and 51‑dimensional bookmaker odds, achieving up to 54.5% match‑outcome accuracy, proposing a profit‑condition betting strategy and extending the approach to stock‑price forecasting.
Betting StrategyRandom ForestSVM
0 likes · 21 min read

This article models soccer shooting using simple geometric assumptions, divides the field into three zones, derives hyperbolic trajectories for optimal shooting points, introduces shooting‑equivalent lines, and shows that the best shooting spots are not always closest to the goal.
Sports Analyticsgeometrymathematical modeling
0 likes · 4 min read

This article demonstrates how to use Python, pandas, and Jupyter Notebook to explore a comprehensive World Cup dataset, clean and enrich the data, visualize win and goal statistics for all teams, and finally predict the top three contenders for the 2018 tournament.
PandasPythonSports Analytics
0 likes · 12 min read

This article demonstrates how to retrieve NBA play‑by‑play movement data via the stats.nba.com API, transform it into a pandas DataFrame, enrich it with player names, visualize player trajectories on a basketball court, and compute travel distances, speeds and inter‑player distances using Python libraries.
Movement TrackingNBASports Analytics
0 likes · 19 min read
