TennisEdge's AI model finds no betting value in M. Keys vs Y. Starodubtseva (Paris on 2026-05-16) — the market is efficient, with M. Keys favoured at 1.26.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | M. Keys | Y. Starodubtseva |
|---|---|---|
| Elo ratings-based, surface-weighted |
62.8% | 37.2% |
| Machine learning 29-feature gradient-boosted model |
71.5% | 28.5% |
| Serve / return point-by-point simulation |
57.4% | 42.6% |
| Blend what the bot actually prices off |
63.9% | 36.1% |
| Market implied de-vigged from the opening odds |
73.5% | 26.5% |
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. Keys | hard | 1898 | 91–56 | 147 |
| Y. Starodubtseva | hard | 1636 | 69–53 | 122 |
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 July 27, 2026.
Level at 1–1 over 2 meetings. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| May 16, 2026 | Paris | clay | M. Keys | 2 - 1 |
| April 4, 2026 | Charleston | clay | Y. Starodubtseva | 2 - 0 |
| 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 |
| L | M. Joint | 1 - 2 | Aug. 3, 2026 |
| L | S. Stephens | 1 - 2 | July 28, 2026 |
| L | A. Blinkova | 1 - 2 | June 30, 2026 |
| L | A. Zakharova | 1 - 2 | June 23, 2026 |
| L | E. Navarro | 1 - 2 | June 17, 2026 |
All May 16, 2026 results & picks →
Math-only prediction: no LLM calls used