TennisEdge's AI model finds no betting value in M. Kecmanovic vs K. Khachanov (Hamburg on 2026-05-18) — the market is efficient, with K. Khachanov favoured at 1.60.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | M. Kecmanovic | K. Khachanov |
|---|---|---|
| Elo ratings-based, surface-weighted |
40.3% | 59.7% |
| Machine learning 29-feature gradient-boosted model |
36.8% | 63.2% |
| Serve / return point-by-point simulation |
37.6% | 62.4% |
| Blend what the bot actually prices off |
38.3% | 61.7% |
| Market implied de-vigged from the opening odds |
40.7% | 59.3% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| M. Kecmanovic | hard | 1734 | 98–98 | 196 |
| K. Khachanov | hard | 1781 | 120–84 | 204 |
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. 4, 2026.
| W | M. Zheng | 1 - 2 | Aug. 4, 2026 |
| L | S. Baez | 2 - 1 | July 21, 2026 |
| L | J. M. Cerundolo | 2 - 1 | July 16, 2026 |
| W | K. Feldbausch | 1 - 2 | July 13, 2026 |
| L | J. Sinner | 3 - 2 | June 29, 2026 |
| L | B. Tomic | 2 - 0 | July 30, 2026 |
| L | F. Cobolli | 2 - 3 | July 4, 2026 |
| W | Y. Hanfmann | 3 - 0 | July 2, 2026 |
| W | B. Harris | 3 - 1 | June 30, 2026 |
| L | M. Damm | 0 - 2 | June 24, 2026 |
All May 18, 2026 results & picks →
Math-only prediction: no LLM calls used