Study independently
Explore the public lessons, calculators and reviewed research. AI Research Coach is a separate release and is not active here.
No AI questions are sent from the Academy. Interactive labs calculate locally without a provider.Master the mathematics of sports markets
Learn how quantitative analysts read prices, remove the margin, estimate fair probabilities, test an edge and manage risk — and why most apparent edges disappear under scrutiny.
- 24Lessons
- 4Tracks
- 5Interactive labs
- 24Verified sources
A strategy can be profitable in theory, profitable in a historical sample, and still fail in real execution. This Academy teaches the difference. No guaranteed profits, no live tips — WCWins play uses free virtual Credits.
Find the edge
Discover how sports markets work through academic research, real-world case studies, quantitative models and interactive experiments.
Every source lists what it found, its limitations and what it does not show.Flagship research articles
Read the long form
The Edge Is in the Price, Not in Picking the Winner
Why a team that wins most of the time can still be a bad bet, how to strip the margin out of a price, and why even a careful estimate rarely proves an advantage.
Kelly, Drawdowns and the Danger of a Confident Forecast
The Kelly criterion is the mathematically fastest way to grow a bankroll — if you know the true probability. You never do. Here is what happens when you are wrong, and why the right stake is often far smaller, or zero.
A Profitable Backtest That Never Existed
A +162% return on 27 bets, built from one typo, two impossible timestamps, a duplicated row and a stake no bookmaker would accept. How to audit a backtest before you believe it.
Curriculum · 24 lessons
Full curriculum →Four learning tracks
Each lesson has objectives, worked examples, an experiment, common mistakes, a failure case, primary research and a short knowledge check.
0 of 24 complete on this device
Price Intelligence
Settlement rules, implied probability, bookmaker margin, expected value and the gap between a quoted and an executable price.
Finding and Validating an Edge
Consensus prices, market equivalence, closing line value, football score models, pricing biases and honest backtesting.
- 07Building a consensus fair price 9 min
- 08Line shopping and exact market equivalence 8 min
- 09Closing line value: a diagnostic, not a verdict 8 min
- 10Football score models: Poisson and Dixon–Coles 8 min
- 11The favourite–longshot bias: test it, don't assume it 7 min
- 12Backtesting without fooling yourself 7 min
Risk and Bankroll Science
Kelly and fractional Kelly, uncertainty-aware decisions, drawdowns, correlated exposure, execution costs and model calibration.
Professional Research Lab
Reproduce published studies, catch false positives, weigh conflicting evidence and write a reproducible research report.
Value Labs
All labs →Run the experiment
Deterministic calculators and seeded simulations. Every number comes from tested functions — never from an AI guess.
Lab 1
Fair Odds and Expected Value
Turn a price and a probability estimate into break-even, expected ROI and a sensitivity band — and see when an assumed edge survives uncertainty.
Lab 2Remove the Margin
Enter home, draw and away odds and compare proportional, additive, power and Shin fair probabilities side by side.
Lab 3Kelly and Drawdown
Simulate thousands of synthetic bankroll paths under flat, fixed-fraction, Kelly and uncertainty-aware staking, including what happens when your probability is wrong.
Lab 4Calibration and Backtesting
Score synthetic forecasts with Brier and log loss, read a reliability diagram, split by date and watch a leaky model collapse.
Lab 5Research Replication Challenge
Audit a deliberately flawed synthetic backtest: find the bad price, look-ahead quotes, duplicate rows and unexecutable stakes.
Browse by topic
Research topics
Value 7 foundations · XP checks
All seven →Seven ways to read a match
The seven Value 7 market lessons, each with its server-verified knowledge check. A correct answer can earn XP once per lesson, within the shared weekly cap.