TENNISEDGE.GG

K. Deichmann vs H. Sakatsume — Prediction & Analysis

French Open · WTA French Open - Semi-finals · May 20, 2026 · 10:00 UTC

TennisEdge's AI model finds no betting value in K. Deichmann vs H. Sakatsume (French Open on 2026-05-20) — the market is efficient, with H. Sakatsume favoured at 1.40.

Surface clay Odds K. Deichmann 2.75 · H. Sakatsume 1.40

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: K. Deichmann · H. Sakatsume · head-to-head record · French Open

Model probabilities

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

Method K. Deichmann H. Sakatsume
Elo
ratings-based, surface-weighted
59.8% 40.2%
Machine learning
29-feature gradient-boosted model
70.1% 29.9%
Serve / return
point-by-point simulation
45.5% 54.5%
Blend
what the bot actually prices off
58.5% 41.5%
Market implied
de-vigged from the opening odds
33.7% 66.3%

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

Elo ratings

PlayerSurfaceEloRecordMatches
K. Deichmann hard1522 84–72156
H. Sakatsume hard1653 162–100262

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 14, 2026.

Head to head

H. Sakatsume leads 1–0 over 1 meeting. Full record.

DateEventSurfaceWinnerScore
May 20, 2026French OpenclayH. Sakatsume2 - 1

Recent form

K. Deichmann

L V. Brand 2 - 0 July 19, 2026
L M. L. Carle 2 - 1 July 14, 2026
L T. Zidansek Walk Over July 9, 2026
W A. Prisacariu 1 - 2 July 8, 2026
L T. J. Brockmann 2 - 1 July 1, 2026

H. Sakatsume

L M. Uchijima 2 - 0 Aug. 1, 2026
L M. Hontama 2 - 0 July 30, 2026
W A. Arseneault 0 - 2 July 30, 2026
W C. Wong Hong Yi 1 - 2 July 29, 2026
L F. Crawley 2 - 1 July 22, 2026

All May 20, 2026 results & picks →

Full analysis

Math-only prediction: no LLM calls used