Barcelona Wvs
Servette Chênois W
Half-time grid built from 44% of the 5.43 total xG. Barcelona W: DDWW (2-2-0). Probability 65%.
Match modelThursday 19 November: 24 fixtures clear the HT/FT threshold, with a mean probability of 34%. Highest reading: Barcelona W vs Servette Chênois W, HT Barcelona W / FT Barcelona W at 65%.
The half-time and full-time results predicted together, from a two-half simulation. Sorted by probability; tap a match for its score grid.
Half-time grid built from 44% of the 5.43 total xG. Barcelona W: DDWW (2-2-0). Probability 65%.
Match modelHalf-time grid built from 44% of the 3.60 total xG. Al-Wasl FC won their latest game (WLW). Probability 50%.
Match modelHalf-time grid built from 44% of the 3.30 total xG. Probability 48%.
Match modelFirst halves carry fewer goals, and the model's half-time grid reflects it. Probability 47%.
Match modelThursday 19 November: 24 selections, mean probability 34%. Strongest upcoming reading: Barcelona W vs Servette Chênois W (UEFA Champions League Women) – HT Barcelona W / FT Barcelona W, 65%. Busiest competitions: Brazil Serie A (7), Europe UEFA Champions League Women (5), Iran Persian Gulf Pro League (3).
HT/FT predicts the half-time and full-time results together – nine possible combinations such as 1/1, X/1 or X/X.
Both halves of the prediction must be right; 1/1 loses if the home side is level at the break and wins later.
The model simulates both halves from the same xG split. Strong favourites tend to produce 1/1 or X/1; tight, low-scoring games produce X/X.
Expected goals for each side come from xGaura's attack and defence ratings, a statistical xG feed and the goal line implied by bookmaker prices. A Poisson model turns those two numbers into the probability of every scoreline, and each market is a sum of cells from that one grid – so the 1X2, goals and BTTS figures for a match always agree. Fair odds are 1 ÷ probability; a price above them is flagged as value. See the methodology or the full grids on mathematical models.
Want combinations instead? Open the accumulators, the pick of the day or the market comparison.
The half-time/full-time market – HT/FT – asks you to predict both the result at the interval and the result at the final whistle. With three possible outcomes at each stage, there are nine combinations, from home/home to away/away. It is a long-odds market by design, and one where a model that understands goal timing has a natural advantage over guesswork.
The model splits each team's expected goals into a first-half share (about 44%) and a second-half share (about 56%). It builds a first-half score grid and a second-half grid, then combines them: for every possible half-time score, it adds every possible second-half score to reach a full-time score. Grouping the results by half-time outcome and full-time outcome produces the nine HT/FT probabilities, which always sum to 100%.
Many bettors back home/home on any strong favourite, but the favourite has to be ahead at half-time as well as at full time. With first-half expected goals well below one for most teams, a favourite at 65% to win the match may be only 35–40% to lead at the break. The page shows both legs' implications in a single probability, which helps avoid paying short odds for a combination that is less likely than it feels.
Because nine outcomes share the probability, prices are long and bookmaker margins are spread thin across each. Value tends to appear in the draw/favourite combinations, where the market sometimes underestimates how often a goalless first half precedes a decisive second. Compare the fair odds column with the best price before deciding.
The 44/56 split is a league-wide average. Teams that start fast, or managers who change things at half-time, can depart from it. The model also assumes the second half is independent of the first, while real games have game-state effects. Treat HT/FT as a small-stake market and judge it over many weeks.
See half-time result for the first leg alone and 1X2 predictions for the full-time result alone. Settled on the half-time score and the 90-minute score. Over 18s only.
For a home favourite projected at 1.9 against 0.8, the model might read home/home at 30%, draw/home at 22%, draw/draw at 13%, and the remaining six combinations sharing the rest. Draw/home at fair odds of about 4.50 is often a more interesting price than home/home at 3.30, because the market tends to concentrate its attention on the favourite's double.
A final tip: if you like the favourite to win but not necessarily to lead early, the draw/favourite combination expresses that view at a much longer price than a straight win, while still paying out in one of the most common match patterns – a cautious first half followed by a decisive second.
Nine – three possible half-time results times three full-time results.
Level at half-time, home win at full time.
Each side's expected goals come from attack and defence ratings plus market prices. A Poisson grid turns them into the chance of every score, and the HT/FT figure is the sum of the matching cells. The list is sorted by that probability.
How often the model expects the pick to win. 70% means about seven wins and three losses in ten matches with the same numbers.
Yes – every pick is graded on the 90-minute score and kept on the Yesterday tab and the track record.
Enter your email once to unlock the full score grids, stake guides and the 90-day leaderboard on this device. No password, no payment. We send at most one weekly model report; unsubscribe any time.
18+ · See our privacy policy.