NeuPortal blog
AI × Markets, in plain English
Clear guides as we build in the open — knowledge, never signals.
-
How to Prove a Prediction Was Made Before the Event (with OpenTimestamps)
Anyone can claim they called it. Here's how OpenTimestamps anchors a prediction to Bitcoin so its timing is provable — and how you verify it yourself.
Read → -
What Is Kalshi? How Regulated Prediction Markets Work
What is Kalshi? A plain-English guide to the CFTC-regulated event exchange, how contract prices become probabilities, and how it differs from Polymarket.
Read → -
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 →