TennisEdge's AI model finds no betting value in T. Paul vs B. Van De Zandschulp (London on 2026-06-17) — the market is efficient, with T. Paul favoured at 1.28.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | T. Paul | B. Van De Zandschulp |
|---|---|---|
| Elo ratings-based, surface-weighted |
78.4% | 21.6% |
| Machine learning 29-feature gradient-boosted model |
65.3% | 34.7% |
| Blend what the bot actually prices off |
76.7% | 23.3% |
| Market implied de-vigged from the opening odds |
74.6% | 25.4% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| T. Paul | hard | 1894 | 154–80 | 234 |
| B. Van De Zandschulp | hard | 1749 | 108–84 | 192 |
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 28, 2026.
B. Van De Zandschulp leads 2–1 over 3 meetings. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| June 18, 2026 | London | grass | T. Paul | 2 - 0 |
| Nov. 1, 2023 | ATP Paris | hard | B. Van De Zandschulp | 2 - 1 |
| Sept. 14, 2023 | ATP Davis Cup - World Group | — | B. Van De Zandschulp | 2 - 0 |
| L | K. Majchrzak | 2 - 0 | July 28, 2026 |
| L | H. Hurkacz | 3 - 1 | July 3, 2026 |
| W | S. Kwon | 0 - 3 | July 1, 2026 |
| W | A. Muller | 0 - 3 | June 29, 2026 |
| L | N. Djokovic | 1 - 2 | June 26, 2026 |
| L | J. Faria | 0 - 2 | July 21, 2026 |
| L | D. Vallejo | 1 - 2 | July 15, 2026 |
| W | T. Daniel | 2 - 0 | July 14, 2026 |
| L | R. Safiullin | 3 - 2 | July 1, 2026 |
| W | A. Kovacevic | 1 - 3 | June 29, 2026 |
All June 17, 2026 results & picks →
Math-only prediction: no LLM calls used