TennisEdge's AI model finds no betting value in E. Nava vs I. Buse (Wimbledon on 2026-06-29) — the market is efficient, with I. Buse favoured at 1.66.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | E. Nava | I. Buse |
|---|---|---|
| Elo ratings-based, surface-weighted |
44.5% | 55.5% |
| Machine learning 29-feature gradient-boosted model |
57.3% | 42.7% |
| Blend what the bot actually prices off |
50.9% | 49.1% |
| Market implied de-vigged from the opening odds |
43.0% | 57.0% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
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 March 19, 2026.
I. Buse leads 1–0 over 1 meeting. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| June 29, 2026 | Wimbledon | grass | I. Buse | 3 - 1 |
| L | I. Buse | 1 - 3 | June 29, 2026 |
| L | H. Stewart | 1 - 2 | June 20, 2026 |
| L | T. Daniel | 2 - 0 | June 11, 2026 |
| W | P. Boscardin Dias | 1 - 2 | June 9, 2026 |
| W | H. Squire | 0 - 2 | June 6, 2026 |
| L | T. M. Etcheverry | 2 - 0 | July 23, 2026 |
| W | K. Feldbausch | 1 - 2 | July 22, 2026 |
| W | V. Kopriva | 1 - 2 | July 20, 2026 |
| L | S. Tsitsipas | 2 - 0 | July 14, 2026 |
| L | J. Brooksby | 3 - 0 | July 1, 2026 |
All June 29, 2026 results & picks →
The ML model suggests a 5.9% edge on Nava, primarily driven by 'hard_elo_diff' and age factors. However, this creates a dangerous blind spot for the surface. Buse is listed as a 'Strong Specialist' and recently secured high-quality wins over Tsitsipas and Giron on grass, while Nava lost his only recent grass match to a lower-ranked opponent (Stewart). Furthermore, the Market-Elo Trend indicates Buse is 'lagging results' (undervalued), which directly contradicts the model's signal that Nava is the value side. With Buse having 5 days of rest, the fatigue edge for Nava is negligible. The model's edge appears to be a false positive driven by surface-agnostic features.