TENNISEDGE.GG

C. Ugo Carabelli vs A. Shevchenko — Prediction & Analysis

Rome · ATP Rome - 1/64-finals · May 6, 2026 · 11:00 UTC

TennisEdge's AI model finds no betting value in C. Ugo Carabelli vs A. Shevchenko (Rome on 2026-05-06) — the market is efficient, with C. Ugo Carabelli favoured at 1.56.

Surface clay Odds C. Ugo Carabelli 1.56 · A. Shevchenko 2.42

Verdict: no bet

The model found no value at current prices — the market has this one priced about right. That verdict is part of the public record too.
Profiles: C. Ugo Carabelli · A. Shevchenko · head-to-head record · Rome

Model probabilities

Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.

Method C. Ugo Carabelli A. Shevchenko
Elo
ratings-based, surface-weighted
74.7% 25.3%
Machine learning
29-feature gradient-boosted model
85.1% 14.9%
Serve / return
point-by-point simulation
54.1% 45.9%
Blend
what the bot actually prices off
71.3% 28.7%
Market implied
de-vigged from the opening odds
60.8% 39.2%

We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?

Elo ratings

PlayerSurfaceEloRecordMatches
C. Ugo Carabelli clay1796 208–111319
A. Shevchenko clay1681 128–89217

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 20, 2026.

Head to head

A. Shevchenko leads 1–0 over 1 meeting. Full record.

DateEventSurfaceWinnerScore
May 6, 2026RomeclayA. Shevchenko2 - 1

Recent form

C. Ugo Carabelli

L C. Norrie 0 - 2 Aug. 4, 2026
L T. Droguet 2 - 1 July 20, 2026
L R. A. Burruchaga 2 - 1 July 16, 2026
W P. Carreno-Busta 1 - 2 July 15, 2026
W M. Topo 1 - 2 July 14, 2026

A. Shevchenko

L K. Jacquet 1 - 2 Aug. 1, 2026
L J-L. Struff 2 - 1 July 21, 2026
L S. Tsitsipas 1 - 2 July 18, 2026
W Q. Halys 0 - 2 July 17, 2026
W D. Stricker 2 - 0 July 17, 2026

All May 6, 2026 results & picks →

Full analysis

Math-only prediction: no LLM calls used