TennisEdge's AI bot is backing M. Kessler (moneyline) in M. Kessler vs M. Keys (Eastbourne on 2026-06-25).
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | M. Kessler | M. Keys |
|---|---|---|
| Elo ratings-based, surface-weighted |
31.0% | 69.0% |
| Machine learning 29-feature gradient-boosted model |
35.4% | 64.6% |
| Serve / return point-by-point simulation |
30.3% | 69.7% |
| Blend what the bot actually prices off |
32.2% | 67.8% |
| Market implied de-vigged from the opening odds |
26.2% | 73.8% |
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. Kessler | hard | 1792 | 101–54 | 155 |
| M. Keys | hard | 1898 | 91–56 | 147 |
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.
M. Keys leads 2–0 over 2 meetings. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| June 25, 2026 | Eastbourne | grass | M. Keys | 2 - 0 |
| Jan. 6, 2026 | WTA Brisbane | hard | M. Keys | 2 - 0 |
| W | C. Brace | 2 - 0 | Aug. 3, 2026 |
| L | R. Zarazua | 2 - 0 | July 29, 2026 |
| L | A. Sabalenka | 2 - 0 | July 1, 2026 |
| W | O. Oliynykova | 0 - 2 | June 29, 2026 |
| L | M. Keys | 0 - 2 | June 25, 2026 |
| L | L. Samsonova | 2 - 1 | July 27, 2026 |
| L | L. Noskova | 0 - 2 | July 6, 2026 |
| W | A. Anisimova | 1 - 2 | July 4, 2026 |
| W | K. Swan | 0 - 2 | July 2, 2026 |
| W | K. Day | 1 - 2 | June 30, 2026 |
All June 25, 2026 results & picks →
The model identifies a 5.0% edge on M. Kessler derived from a 31.2% win probability. However, the Market Trend framework explicitly warns that Kessler is 'possibly over-priced' (market chasing form) while Keys is 'possibly undervalued' (market lagging results). Keys' superior recent form (11-4 vs 7-8) and grass record (4-1 vs 2-2) validate the market's higher assessment, suggesting the model has underestimated Keys' current level. While the qualitative analysis flips the value to Keys, the 1.28 odds fall under the 'Strong Favorite Warning', offering insufficient risk/reward to recommend a bet.