Match model — probabilities and prices

Monday 10 August 2026 · 3 matches · 3 competitions · generated 2026-08-09 08:49 UTC
Model output, not advice. These are probabilities from a statistical model, published for transparency about how it performs. They are not tips and not financial advice. In backtests this model does not reliably beat closing prices, which is the only benchmark that matters, so expect selections here to lose money over time. 18+. Gambling is addictive; if it stops being a modelling exercise, stop.
DEN1 1 EFL 1 P1 1

Best value today across all competitions, ranked by expected value rather than by how likely they are to win

LeagueMatchSelectionModelFairBookEVStake
EFLPlymouthvExeter CityExeter City A thin data22.1%4.535.82+28.4%
DEN1SilkeborgvOdenseSilkeborg H40.2%2.492.62+5.4%
P1Santa ClaravNacionalNacional A24.2%4.134.20+1.8%
P1Santa ClaravNacionalDraw29.8%3.363.32-1.1%
DEN1SilkeborgvOdenseDraw24.9%4.013.64-9.3%
EFLPlymouthvExeter CityDraw thin data20.1%4.984.47-10.1%
P1Santa ClaravNacionalSanta Clara H46.0%2.171.88-13.5%
EFLPlymouthvExeter CityPlymouth H thin data57.8%1.731.46-15.7%
DEN1SilkeborgvOdenseOdense A34.9%2.872.39-16.7%

Stake is blank unless a selection clears every gate: positive expected value, at least 5 percentage points of edge over the de-vigged line, and not more than 25 (a disagreement that large is usually the model missing something, not an opportunity). Most rows will be blank most days. Selections marked longshot are below 10% — their EV figure divides by a very small number and should not be trusted. thin data means one side has too few matches in the model's history for its rating to mean anything; the huge edge shown is the model's ignorance, not the market's mistake.

Best goal markets over/under and both teams to score, ranked by expected value

Kept separate from the match-winner table because they are a different bet: independent of who wins, driven by the total-goals distribution rather than the difference between the two sides. Worth a look for two reasons — a goal model is being asked the question it was actually built to answer, and a totals line is far less correlated with the rest of a slip than another favourite. Against that, books charge more margin here than on the match winner, so a given edge has further to travel.

How much this model actually knows about goals. Measured on out-of-fold predictions during training, not on the fixtures below:
LeagueMatchMarketPickModelFairBookEVStake
DEN1SilkeborgvOdenseTotalsOver3.541.0%2.445.57+128.5%3.00%
EFLPlymouthvExeter CityTotalsOver3.5 thin data30.6%3.276.56+100.9%
EFLPlymouthvExeter CityTotalsOver2.5 thin data51.9%1.933.57+85.5%
DEN1SilkeborgvOdenseTotalsOver2.562.3%1.612.86+78.4%
EFLPlymouthvExeter CityBTTSYes thin data53.5%1.873.08+64.8%
P1Santa ClaravNacionalTotalsOver2.533.9%2.954.68+58.4%3.00%
P1Santa ClaravNacionalTotalsOver1.560.4%1.662.52+52.3%3.00%
DEN1SilkeborgvOdenseTotalsOver1.582.9%1.211.84+52.1%
DEN1SilkeborgvOdenseBTTSYes60.2%1.662.41+45.1%3.00%
EFLPlymouthvExeter CityTotalsOver1.5 thin data75.7%1.321.85+40.4%
P1Santa ClaravNacionalTotalsOver3.515.8%6.328.30+31.3%
P1Santa ClaravNacionalBTTSYes43.1%2.323.02+30.1%3.00%

One row per market per match: the side the model prefers. The two sides of a two-way line are near mirror images, so showing both would double the table without adding anything. Edges are measured against each pair de-vigged on its own, not against the match-winner margin — books load goals markets more heavily, and borrowing the 1X2 overround here would flatter every row.

Same-match combinations priced from the joint distribution, so correlation is handled correctly

The vs naive column is how far a bookmaker would be off if they priced the combination by multiplying the two legs together. A large positive number means the events happen together more often than independence implies — draws and low-scoring games, for instance — so a multiplied price is too generous.

MatchCombinationModelFairvs naiveBookEV
PlymouthvExeter CityAway + Away clean sheet12.9%7.72+149%
SilkeborgvOdenseAway + Away clean sheet12.6%7.95+136%
Santa ClaravNacionalAway + Away clean sheet17.1%5.86+114%
SilkeborgvOdenseBTTS No + Under 2.526.6%3.76+100%
Santa ClaravNacionalBTTS Yes + Over 2.526.5%3.77+99%
SilkeborgvOdenseHome + Home clean sheet18.8%5.32+82%
SilkeborgvOdenseDraw + Under 2.515.0%6.68+69%
PlymouthvExeter CityBTTS No + Under 2.535.8%2.79+66%
PlymouthvExeter CityHome + Home clean sheet25.2%3.96+64%
Santa ClaravNacionalHome + Home clean sheet29.0%3.45+58%
PlymouthvExeter CityDraw + Under 2.519.0%5.26+55%
PlymouthvExeter CityBTTS Yes + Over 2.542.8%2.34+50%
Santa ClaravNacionalBTTS No + Under 2.553.1%1.88+33%
SilkeborgvOdenseBTTS Yes + Over 2.553.6%1.86+33%
Santa ClaravNacionalHome + Over 2.518.9%5.29+33%
Santa ClaravNacionalDraw + Under 2.527.4%3.65+32%
Santa ClaravNacionalAway + Over 2.510.6%9.44+23%
PlymouthvExeter CityHome + Over 2.530.0%3.34+20%
SilkeborgvOdenseHome + BTTS No18.8%5.32+18%
PlymouthvExeter CityHome + BTTS No25.2%3.96+17%

Accumulators shown with what they cost you

Legs from different matches are independent, so the probabilities multiply — and so does the bookmaker's margin. The final column is the share of fair value lost to compounding vig at 5% per leg, before your model is even wrong about anything. Accumulators are on this page because people want them, not because they are a good idea.

LegsNModelFairBookEVMargin cost
Plymouth v Exeter City — over 2.5 goals
Silkeborg v Odense — over 2.5 goals
Santa Clara v Nacional — over 1.5 goals thin data
319.5%5.1225.79+403.9%−14%
Silkeborg v Odense — over 2.5 goals
Plymouth v Exeter City — both teams to score
Santa Clara v Nacional — over 1.5 goals thin data
320.1%4.9722.25+347.8%−14%
Plymouth v Exeter City — over 2.5 goals
Silkeborg v Odense — over 1.5 goals thin data
243.0%2.326.56+182.1%−9%
Plymouth v Exeter City — both teams to score
Silkeborg v Odense — over 1.5 goals thin data
244.3%2.265.65+150.7%−9%
Plymouth v Exeter City — over 2.5 goals
Santa Clara v Nacional — over 1.5 goals
Silkeborg v Odense — over 1.5 goals thin data
326.0%3.8516.54+329.6%−14%
Silkeborg v Odense — over 2.5 goals
Plymouth v Exeter City — both teams to score thin data
233.3%3.008.82+194.0%−9%
Plymouth v Exeter City — both teams to score
Santa Clara v Nacional — over 1.5 goals
Silkeborg v Odense — over 1.5 goals thin data
326.8%3.7414.26+281.8%−14%
Plymouth v Exeter City — over 2.5 goals
Silkeborg v Odense — over 2.5 goals thin data
232.4%3.0910.22+230.9%−9%
Plymouth v Exeter City — over 2.5 goals
Silkeborg v Odense — over 2.5 goals
Santa Clara v Nacional — under 3.5 goals thin data
327.2%3.6711.68+218.2%−14%
Silkeborg v Odense — over 2.5 goals
Plymouth v Exeter City — both teams to score
Santa Clara v Nacional — under 3.5 goals thin data
328.1%3.5610.08+182.8%−14%

By competition 3 fixtures across 3 competitions · 9/9 selections priced

DEN1 (1 match) all days →
Best value in DEN1
MatchSelectionModelFairBookEVStake
SilkeborgvOdenseSilkeborg H40.2%2.492.62+5.4%
SilkeborgvOdenseDraw24.9%4.013.64-9.3%
SilkeborgvOdenseOdense A34.9%2.872.39-16.7%

Stake is blank unless a selection clears every gate: positive expected value, at least 5 percentage points of edge over the de-vigged line, and not more than 25 (a disagreement that large is usually the model missing something, not an opportunity). Most rows will be blank most days. Selections marked longshot are below 10% — their EV figure divides by a very small number and should not be trusted. thin data means one side has too few matches in the model's history for its rating to mean anything; the huge edge shown is the model's ignorance, not the market's mistake.

Goal markets in DEN1
MatchMarketPickModelFairBookEVStake
SilkeborgvOdenseTotalsOver3.541.0%2.445.57+128.5%3.00%
SilkeborgvOdenseTotalsOver2.562.3%1.612.86+78.4%
SilkeborgvOdenseTotalsOver1.582.9%1.211.84+52.1%
SilkeborgvOdenseBTTSYes60.2%1.662.41+45.1%3.00%

One row per market per match: the side the model prefers. The two sides of a two-way line are near mirror images, so showing both would double the table without adding anything. Edges are measured against each pair de-vigged on its own, not against the match-winner margin — books load goals markets more heavily, and borrowing the 1X2 overround here would flatter every row.

Silkeborg HOME v Odense AWAY

17:00 · DEN1 · expected goals Silkeborg 1.78 – 1.46 Odense
Silkeborg 40% · draw 25% · Odense 35%
ModelMarketBook oddsEdge
Silkeborg40.2%35.6%2.62+4.6pp
Draw24.9%25.2%3.64-0.2pp
Odense34.9%39.2%2.39-4.4pp
Over 1.582.9%51.4%1.84+31.5pp
Under 1.517.1%48.6%1.94-31.5pp
Over 2.562.3%35.9%2.86+26.4pp
Under 2.537.7%64.1%1.60-26.4pp
Over 3.541.0%18.9%5.57+22.1pp
Under 3.559.0%81.1%1.30-22.1pp
BTTS Yes60.2%45.4%2.41+14.8pp
BTTS No39.8%54.6%2.00-14.8pp
Silkeborg win
40%
Draw
25%
Odense win
35%
Silkeborg or draw
65%
either team
75%
draw or Odense
60%
Over 1.5
83%
Under 1.5
17%
Over 2.5
62%
Under 2.5
38%
Over 3.5
41%
Under 3.5
59%
BTTS Yes
60%
BTTS No
40%
Silkeborg clean sheet
23%
Odense clean sheet
17%
Likeliest scores: 1–1 11% · 2–1 9% · 1–2 7% · 2–2 7%
Correlated combinations
  • Odense win + Odense clean sheet — 13% (fair 7.95); naive multiplication would say 5%, off by +136%
  • BTTS No + Under 2.5 — 27% (fair 3.76); naive multiplication would say 13%, off by +100%
  • Silkeborg win + Silkeborg clean sheet — 19% (fair 5.32); naive multiplication would say 10%, off by +82%
  • Draw + Under 2.5 — 15% (fair 6.68); naive multiplication would say 9%, off by +69%
EFL (1 match) all days →
Best value in EFL
MatchSelectionModelFairBookEVStake
PlymouthvExeter CityExeter City A thin data22.1%4.535.82+28.4%
PlymouthvExeter CityDraw thin data20.1%4.984.47-10.1%
PlymouthvExeter CityPlymouth H thin data57.8%1.731.46-15.7%

Stake is blank unless a selection clears every gate: positive expected value, at least 5 percentage points of edge over the de-vigged line, and not more than 25 (a disagreement that large is usually the model missing something, not an opportunity). Most rows will be blank most days. Selections marked longshot are below 10% — their EV figure divides by a very small number and should not be trusted. thin data means one side has too few matches in the model's history for its rating to mean anything; the huge edge shown is the model's ignorance, not the market's mistake.

Goal markets in EFL
MatchMarketPickModelFairBookEVStake
PlymouthvExeter CityTotalsOver3.5 thin data30.6%3.276.56+100.9%
PlymouthvExeter CityTotalsOver2.5 thin data51.9%1.933.57+85.5%
PlymouthvExeter CityBTTSYes thin data53.5%1.873.08+64.8%
PlymouthvExeter CityTotalsOver1.5 thin data75.7%1.321.85+40.4%

One row per market per match: the side the model prefers. The two sides of a two-way line are near mirror images, so showing both would double the table without adding anything. Edges are measured against each pair de-vigged on its own, not against the match-winner margin — books load goals markets more heavily, and borrowing the 1X2 overround here would flatter every row.

Plymouth HOME v Exeter City AWAY

19:00 · EFL · expected goals Plymouth 1.62 – 1.14 Exeter City
Thin data: Plymouth 13 matches, Exeter City 11 in this model's history. Ratings that sparse sit near the league average, which flatters the weaker side badly when the two come from different divisions. Shown for completeness, not as a forecast.
Plymouth 58% · draw 20% · Exeter City 22%
ModelMarketBook oddsEdge
Plymouth57.8%65.3%1.46-7.4pp
Draw20.1%19.9%4.47+0.2pp
Exeter City22.1%14.8%5.82+7.2pp
Over 1.575.7%50.6%1.85+25.2pp
Under 1.524.3%49.4%1.90-25.2pp
Over 2.551.9%27.4%3.57+24.5pp
Under 2.548.1%72.6%1.35-24.5pp
Over 3.530.6%15.8%6.56+14.9pp
Under 3.569.4%84.2%1.23-14.9pp
BTTS Yes53.5%34.4%3.08+19.1pp
BTTS No46.5%65.6%1.62-19.1pp
Plymouth win
58%
Draw
20%
Exeter City win
22%
Plymouth or draw
78%
either team
80%
draw or Exeter City
42%
Over 1.5
76%
Under 1.5
24%
Over 2.5
52%
Under 2.5
48%
Over 3.5
31%
Under 3.5
69%
BTTS Yes
54%
BTTS No
46%
Plymouth clean sheet
32%
Exeter City clean sheet
20%
Likeliest scores: 1–1 12% · 1–0 10% · 2–1 9% · 2–0 8%
Correlated combinations
  • Exeter City win + Exeter City clean sheet — 13% (fair 7.72); naive multiplication would say 5%, off by +149%
  • BTTS No + Under 2.5 — 36% (fair 2.79); naive multiplication would say 22%, off by +66%
  • Plymouth win + Plymouth clean sheet — 25% (fair 3.96); naive multiplication would say 15%, off by +64%
  • Draw + Under 2.5 — 19% (fair 5.26); naive multiplication would say 12%, off by +55%
P1 (1 match) all days →
Best value in P1
MatchSelectionModelFairBookEVStake
Santa ClaravNacionalNacional A24.2%4.134.20+1.8%
Santa ClaravNacionalDraw29.8%3.363.32-1.1%
Santa ClaravNacionalSanta Clara H46.0%2.171.88-13.5%

Stake is blank unless a selection clears every gate: positive expected value, at least 5 percentage points of edge over the de-vigged line, and not more than 25 (a disagreement that large is usually the model missing something, not an opportunity). Most rows will be blank most days. Selections marked longshot are below 10% — their EV figure divides by a very small number and should not be trusted. thin data means one side has too few matches in the model's history for its rating to mean anything; the huge edge shown is the model's ignorance, not the market's mistake.

Goal markets in P1
MatchMarketPickModelFairBookEVStake
Santa ClaravNacionalTotalsOver2.533.9%2.954.68+58.4%3.00%
Santa ClaravNacionalTotalsOver1.560.4%1.662.52+52.3%3.00%
Santa ClaravNacionalTotalsOver3.515.8%6.328.30+31.3%
Santa ClaravNacionalBTTSYes43.1%2.323.02+30.1%3.00%

One row per market per match: the side the model prefers. The two sides of a two-way line are near mirror images, so showing both would double the table without adding anything. Edges are measured against each pair de-vigged on its own, not against the match-winner margin — books load goals markets more heavily, and borrowing the 1X2 overround here would flatter every row.

Santa Clara HOME v Nacional AWAY

19:15 · P1 · expected goals Santa Clara 1.18 – 0.85 Nacional
Santa Clara 46% · draw 30% · Nacional 24%
ModelMarketBook oddsEdge
Santa Clara46.0%50.5%1.88-4.5pp
Draw29.8%27.8%3.32+1.9pp
Nacional24.2%21.6%4.20+2.6pp
Over 1.560.4%37.3%2.52+23.1pp
Under 1.539.6%62.7%1.50-23.1pp
Over 2.533.9%21.2%4.68+12.7pp
Under 2.566.1%78.8%1.26-12.7pp
Over 3.515.8%12.1%8.30+3.7pp
Under 3.584.2%87.9%1.14-3.7pp
BTTS Yes43.1%32.5%3.02+10.6pp
BTTS No56.9%67.5%1.45-10.6pp
Santa Clara win
46%
Draw
30%
Nacional win
24%
Santa Clara or draw
76%
either team
70%
draw or Nacional
54%
Over 1.5
60%
Under 1.5
40%
Over 2.5
34%
Under 2.5
66%
Over 3.5
16%
Under 3.5
84%
BTTS Yes
43%
BTTS No
57%
Santa Clara clean sheet
43%
Nacional clean sheet
31%
Likeliest scores: 1–0 15% · 1–1 14% · 0–0 14% · 0–1 11%
Correlated combinations
  • Nacional win + Nacional clean sheet — 17% (fair 5.86); naive multiplication would say 8%, off by +114%
  • BTTS Yes + Over 2.5 — 27% (fair 3.77); naive multiplication would say 13%, off by +99%
  • Santa Clara win + Santa Clara clean sheet — 29% (fair 3.45); naive multiplication would say 18%, off by +58%
  • BTTS No + Under 2.5 — 53% (fair 1.88); naive multiplication would say 40%, off by +33%