Sports Analytics Weekly by kubeia.io - 45/2025
- Week 45
- Week 44
- Week 43
- Week 42
- Week 41
- Week 40
- Week 39
- Week 38
- Week 37
- Week 36
- Week 35
- Week 33
- Week 32
- Week 31
- Week 30
- Week 29
- Week 28
- Week 27
- Week 26
- Week 25
- Week 24
- Week 23
- Week 22
- Week 21
- Week 19
- Week 17
- Week 16
- Week 14
- Week 13
- Week 12
- Week 11
- Week 10
- Week 9
- Week 7
- Week 6
- Week 5
- Week 4
- Week 3
- Week 2
- Week 1
🎲 Betting
Betting scandals galore
sportismadeforbetting.com - Scott
So after my recent post on the NBA scandal, there are a few more scandals on the horizon. Turkish footballThe 'best' one has to be the Turkish football referee scandal.
đź“ť Sports Analytics
This is How Football Teams Create Scoring Opportunities
substack.com - Alex Marin Felices
The following summary critically reviews the research paper titled “Visualizing a team’s goal chances in soccer from attacking events: A Bayesian inference approach“ by Gavin A. Whitaker, Ricardo Silva, and Daniel Edwards. All data, figures, and analysis presented here are drawn from their original work; I do not claim any authorship or ownership of the content. This summary has been written to provide a concise and technically informed synthesis of the paper’s findings, methodologies, and implications, while maintaining fidelity to the authors’ intellectual contributions.
🤖 Machine Learning
Pushp-Kharat1/PkBoost: PKBoost: Adaptive GBDT for Concept Drift
github.com - Pushp Kharat
Gradient boosting that adjusts to concept drift in imbalanced multi-class data. Built from scratch in Rust, PKBoost (Performance-Based Knowledge Booster) manages changing data distributions in fraud detection with a fraud rate of 0.2%. It shows less than 2% degradation under drift. In comparison, XGBoost experiences a 31.8% drop and LightGBM a 42.5% drop. PKBoost outperforms XGBoost by 10-18% on the Standard dataset when no drift is applied. It employs information theory with Shannon entropy and Newton Raphson to identify shifts in rare events and trigger an adaptive "metamorphosis" for real-time recovery.
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
googleapis.com - Prior Labs Team
The first tabular foundation model, TabPFN, and its successor TabPFNv2 have impacted tabular
AI substantially, with dozens of methods building on it and hundreds of applications across
different use cases.
This report introduces TabPFN-2.5, the next generation of our tabular foundation model, scaling
to 20Ă— data cells compared to TabPFNv2. On industry standard benchmarks with up to 50,000
data points and 2,000 features, TabPFN-2.5 substantially outperforms tuned tree-based models
and matches the accuracy of AutoGluon 1.4, a complex four-hour tuned ensemble that even
includes the previous TabPFNv2.
For production use cases, we introduce a new distillation engine that converts TabPFN-2.5 into
a compact MLP or tree ensemble, preserving most of its accuracy while delivering orders-ofmagnitude lower latency and plug-and-play deployment.
This new release will immediately strengthen the performance of the many applications and
methods already built on the TabPFN ecosystem.
🌩 Forecasting
Unlocking Predictive Power: Harnessing Permutation Entropy for Superior Time-Series Forecasting
medium.com - Valeriy Manokhin
Why do some financial market trends defy prediction while others follow clear patterns? Understanding the predictability of time series can unlock predictive power — and permutation entropy is a key tool for this.The predictability of time series data plays a key role in forecasting, influencing the choice of suitable forecasting methods. Various metrics have been developed to quantify predictability, and their impact on forecasting accuracy remains an active area of research.