TennisEdge's AI model finds no betting value in L. van Assche vs P. Kypson (French Open on 2026-05-24) — the market is efficient, with P. Kypson favoured at 1.80.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | L. van Assche | P. Kypson |
|---|---|---|
| Elo ratings-based, surface-weighted |
56.2% | 43.8% |
| Machine learning 29-feature gradient-boosted model |
56.4% | 43.6% |
| Serve / return point-by-point simulation |
49.2% | 50.8% |
| Blend what the bot actually prices off |
53.9% | 46.1% |
| Market implied de-vigged from the opening odds |
47.4% | 52.6% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| L. van Assche | hard | 1762 | 101–85 | 186 |
| P. Kypson | hard | 1706 | 118–74 | 192 |
Our own ratings, computed from match results since 2018. Players with fewer than 5 rated matches are omitted rather than shown at a provisional starting value. Last updated Aug. 3, 2026.
| L | T. Droguet | 1 - 2 | Aug. 3, 2026 |
| W | A. Blockx | 2 - 1 | July 26, 2026 |
| W | H. Gaston | 2 - 0 | July 25, 2026 |
| W | A. Rublev | 1 - 2 | July 24, 2026 |
| W | P. Carreno-Busta | 2 - 1 | July 23, 2026 |
| L | T. Fritz | 3 - 0 | July 2, 2026 |
| W | M. McDonald | 3 - 1 | June 30, 2026 |
| L | A. Vukic | 2 - 1 | May 6, 2026 |
| W | T. Droguet | 2 - 1 | May 5, 2026 |
| W | J. Pinnington Jones | 2 - 1 | May 4, 2026 |
All May 24, 2026 results & picks →
Math-only prediction: no LLM calls used