Notes from the workshop. Lessons learned from building ML models, insights from failed experiments, and technical deep-dives into what actually works.
Jun 23, 2026
14 min read
> kairox storm
KairoX Storm evaluated across La Liga, Premier League, and Bundesliga. Bundesliga produced the best AUC and the only consistently negative ROI. A cross-league investigation into market efficiency, MC-Gamma failure, and why predictive accuracy and betting edge are not the same thing.
Jun 9, 2026
12 min read
> kairox tempo
Seven XGBoost runs on the same La Liga dataset land within 0.0025 log-loss of each other. Their away-betting ROI diverges by 11 percentage points. Walk-forward evidence that the metric you are optimising is not measuring what you think.