TennisEdge's AI model finds no betting value in E. Micic vs A. Koevermans (Caldas da Rainha on 2026-09-15) — the market is efficient, with A. Koevermans favoured at 1.24.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | E. Micic | A. Koevermans |
|---|---|---|
| Elo ratings-based, surface-weighted |
30.9% | 69.1% |
| Machine learning 29-feature gradient-boosted model |
28.5% | 71.5% |
| Serve / return point-by-point simulation |
80.0% | 20.1% |
| Blend what the bot actually prices off |
46.4% | 53.6% |
| Market implied de-vigged from the opening odds |
26.1% | 73.9% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| E. Micic | hard | 1485 | 75–76 | 151 |
| A. Koevermans | hard | 1647 | 58–49 | 107 |
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 Sept. 9, 2026.
| L | X. Gao | 1 - 2 | Sept. 9, 2026 |
| L | C. Werner | 2 - 0 | Sept. 3, 2026 |
| W | P. Isakova | 2 - 0 | Sept. 2, 2026 |
| L | V. Podrez | 0 - 2 | Aug. 3, 2026 |
| W | G. Garcia-Perez | 2 - 0 | Aug. 2, 2026 |
| L | C. McNally | 0 - 2 | Aug. 31, 2026 |
| W | M. Bolkvadze | 0 - 2 | Aug. 28, 2026 |
| W | L. Klimovicova | 2 - 0 | Aug. 26, 2026 |
| W | C. Monnet | 2 - 0 | Aug. 24, 2026 |
| L | J. Burrage | 1 - 2 | Aug. 12, 2026 |
All Sept. 15, 2026 results & picks →