How StackPlays Works

Everything you need to know about our AI-powered value betting predictions

Step 1

Collect

We gather live odds, team stats, xG, injuries, and news from multiple data sources every 8 hours.

Step 2

Analyze

Our ML ensemble processes 200+ features per match to find genuine mathematical edge.

Step 3

Filter

Only predictions with 5%+ edge and 50%+ confidence pass our quality gates. 0-4 picks per day.

Understanding Your Dashboard

Best Bet of the Day

Every day, our ranking system selects the best value bet by computing a composite score based on:

Edge25%

How much value vs the market

Confidence20%

Model certainty in prediction

Expected Value15%

Risk-adjusted return potential

Liquidity15%

Odds availability & quality

Historical25%

Past accuracy for this market type

Example:A match with Score 87.4 means it ranked in the top tier across all five factors. Only the single best bet each day gets the #1 badge.

Predictions Page

Shows all upcoming value bet predictions. You can sort by:

Rank ScoreDefault. Best overall predictions first (composite score).
TimeChronological. Earliest kickoff first. Gold badges only show in Rank Score sort.
EdgeHighest mathematical edge first.
ConfidenceHighest model confidence first.

My Bets

Track your personal betting performance. Star any prediction to add it to your portfolio with a stake amount.

ROI

Return on Investment based on settled bets

Win Rate

Wins / (Wins + Losses), excluding void

Total Profit

Sum of all P/L in units

Streak

Current win/loss streak

Machine Learning Models

StackPlays uses an ensemble of ML models that vote together to generate probability estimates:

XGB
XGBoost

Gradient boosting for structured data

LGB
LightGBM

Fast gradient boosting with leaf-wise growth

CB
CatBoost

Handles categorical features natively

Ensemble Voting:Final probabilities are calibrated using isotonic regression, ensuring that when we say 60% probability, it wins approximately 60% of the time.

200+ Features Per Match

Every prediction is built from a comprehensive dataset:

Team Form & Performance
  • -Goals scored/conceded (last 5, 10 matches)
  • -xG (Expected Goals) from Understat
  • -Clean sheet rates, BTTS rates
  • -Home/away specific form
Odds & Market Data
  • -Live odds from 15+ bookmakers
  • -Pinnacle as sharp reference line
  • -Odds movement tracking
  • -Closing Line Value (CLV) analysis
Historical & H2H
  • -Head-to-head records (last 10 meetings)
  • -Elo rating system per team
  • -League table position & points
  • -Season phase importance factor
Live Factors
  • -Injury reports & squad availability
  • -News sentiment analysis
  • -Lineup strength (30-90 min pre-kickoff)
  • -Rest days between matches

Market Types

We analyze four major betting markets, each with independent quality gates:

1X2 (Match Winner)Min 4% edge

Home win, draw, or away win. Our strongest market historically.

Over/Under GoalsMin 5% edge

Total goals over or under lines (1.5, 2.5, 3.5).

Asian HandicapMin 5% edge

Spread betting with half-line and quarter-line precision.

BTTSMin 5% edge

Both teams to score Yes/No.

Quality Gates

Every prediction must pass strict quality criteria before reaching your dashboard:

5%+
Minimum Edge

Must beat the market by at least 5%

50%+
Min Confidence

Model must be at least 50% confident

0-4
Daily Cap

Maximum 4 picks per day, often fewer

Philosophy:If nothing qualifies, you get zero picks. That's by design. We'd rather give you nothing than a bad bet. Most tipsters spam 15+ picks daily — we take the opposite approach.

13 Leagues Covered

Football

Premier League
England
La Liga
Spain
Bundesliga
Germany
Serie A
Italy
Ligue 1
France
Champions League
Europe
Europa League
Europe
Conference League
Europe
Allsvenskan
Sweden
Eliteserien
Norway
Eredivisie
Netherlands
Primeira Liga
Portugal

Basketball

NBA
USA
NCAA
USA College

Key Concepts Explained

Edge

The difference between our predicted probability and the implied probability from the odds. If we estimate Arsenal has a 60% chance to win but the odds imply only 52%, that's an 8% edge. We only bet when we find genuine edge.

Kelly Criterion

A mathematical formula that determines optimal stake size based on edge size and odds. We use a quarter-Kelly approach (conservative) with a maximum 3% stake per bet. This prevents over-exposure on any single prediction.

Closing Line Value (CLV)

The gold standard metric for prediction quality. If we recommend a bet at 2.10 odds and the line closes at 1.95, we captured CLV. Consistently beating the closing line is the #1 predictor of long-term profit in sports betting.

Value Bet

A bet where the true probability of an outcome is higher than what the bookmaker's odds imply. It's not about picking winners — it's about finding mispriced odds. A value bet can still lose. But over hundreds of bets, the math works in your favor.

Important Disclaimer

Betting Involves Risk

Past performance is not indicative of future results. You can and will have losing streaks. Only bet with money you can afford to lose.

Not Financial Advice

StackPlays provides data-driven predictions for informational purposes. We do not provide financial or betting advice. All decisions are yours.

Transparent Results

All our predictions are tracked and publicly verifiable. Check the Statistics page for full performance data including losing periods.

Frequently Asked Questions