Model accuracy
Predicting a table tennis match before it starts is hard. Published research and rating-based systems top out around 65–70% accuracy — upsets are a structural part of the sport, not a modelling failure. Any product claiming more than that pre-match is overclaiming.
So instead of claiming, we publish. Every prediction is logged before the match with its probability and interval, never revised once the result is known, and scored here against what actually happened.
No resolved predictions yet
Accuracy appears here after real matches complete. Every prediction is logged pre-match and scored against the actual result — nothing to show until the first results are in.
Statistics are computed live from every logged prediction with a known result. Predictions are created once, before the match, and never recomputed afterwards.