TennisEdge's AI model finds no betting value in S. Baez vs A. Michelsen (Geneva on 2026-05-18) — the market is efficient, with S. Baez favoured at 1.57.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | S. Baez | A. Michelsen |
|---|---|---|
| Elo ratings-based, surface-weighted |
77.9% | 22.1% |
| Machine learning 29-feature gradient-boosted model |
63.9% | 36.1% |
| Serve / return point-by-point simulation |
61.9% | 38.1% |
| Blend what the bot actually prices off |
67.9% | 32.1% |
| Market implied de-vigged from the opening odds |
60.2% | 39.8% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| S. Baez | clay | 1776 | 134–76 | 210 |
| A. Michelsen | hard | 1895 | 148–85 | 233 |
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 23, 2026.
A. Michelsen leads 1–0 over 1 meeting. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| May 18, 2026 | Geneva | clay | A. Michelsen | 2 - 0 |
| L | Y. Hanfmann | 2 - 0 | July 23, 2026 |
| W | A. Rinderknech | 2 - 1 | July 22, 2026 |
| W | M. Kecmanovic | 2 - 1 | July 21, 2026 |
| L | A. Rublev | 2 - 0 | July 17, 2026 |
| W | J. De Jong | 0 - 2 | July 16, 2026 |
| W | J-L. Struff | 2 - 1 | Aug. 4, 2026 |
| L | T. Fritz | 2 - 1 | July 31, 2026 |
| W | A. Mannarino | 2 - 0 | July 29, 2026 |
| W | M. McDonald | 2 - 0 | July 28, 2026 |
| W | J. Fearnley | 2 - 0 | July 26, 2026 |
All May 18, 2026 results & picks →
Math-only prediction: no LLM calls used