NeuPortal blog
AI × Markets, in plain English
Clear guides as we build in the open — knowledge, never signals.
-
Expected Goals (xG), Explained: What the Number Actually Measures
Expected goals (xG) explained in plain English: what the number really measures, why xG isn't goals in one match, and how it feeds forecasting models.
Read → -
How a Poisson Model Turns Team Form Into Football Match Probabilities
How a double Poisson model turns attack and defence strength into expected goals, a scoreline matrix, and clean home, draw and away win probabilities.
Read → -
One Method, Four Markets: How AI Forecasting Reads Sports, Crypto, and Prediction Exchanges
Football, Binance, Kalshi and Polymarket look like four different worlds — but one probabilistic method reads them all. A plain-English guide to AI forecasting across markets.
Read → -
How to Read a Match Forecast: Model vs Market, and Why They Disagree
Two forecasts for the same match rarely agree — and the disagreement is the most useful thing on the screen. How to read an AI model against a prediction market.
Read → -
What Is a Brier Score — and Why It's the Only Honest Way to Grade a Forecast
A Brier score is the squared error of a probability — forecasting's lie detector. A plain-English guide with a real worked example, and why calibration beats confidence.
Read → -
Are Prediction Markets Actually Accurate? The Honest Answer
Prediction market prices are surprisingly accurate — with two documented blind spots. How to read the odds, where they break, and why a losing favourite isn't proof they're wrong.
Read → -
Why "The Favourite Lost" Is Never Proof the Odds Were Wrong
A 70% favourite loses three times in ten — by design. Here's why upsets don't mean the model failed, and how to actually tell a good forecast from a bad one.
Read → -
Can AI Break the Sports Betting Exchange? The Honest Answer
AI keeps promising to beat sports betting markets. What a betting exchange really is, the one man who genuinely beat the odds, why the math is brutal — and what AI actually changes.
Read → -
What Is a Prior in Bayesian Forecasting? A Plain-English Guide
A prior is your starting belief before new evidence arrives. What priors are, why they make or break forecasts, and how to build one — explained in plain English with football examples.
Read → -
How AI Detects Anomalies in Market Data: A Technical Primer
Learn how AI models identify unusual patterns in market data — from statistical baselines to deep learning. Education, not trading advice.
Read →