Publications
Research on AI agents, backtesting and audits of market forecasts, and the platform's architecture.
Scoring forecasts
The instinct to grade a forecast by whether it came true is the wrong test. Calibration - when a model says 70% it happens about 70% of the time - is the property that separates a real forecaster from a confident guesser, and it is measurable.
7 min read7 sections
Scoring forecasts
The Brier score grades a probability for a yes/no event. The CRPS does the same job for a full distribution over a number. Here is how it works and why it is a proper scoring rule.
3 min read5 sections
Scoring forecasts
Log loss vs Brier score explained: how each grades a probabilistic forecast, why log loss punishes confident errors harder, and when to use which metric.
6 min read8 sections
Scoring forecasts
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.
5 min read6 sections
Scoring forecasts
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.
4 min read4 sections
Scoring forecasts
A rigorous framework for comparing forecasting models without bias — covering evaluation protocols, metrics, baselines, and statistical significance tests.
7 min read9 sections
Scoring forecasts
Learn how to measure and interpret forecast uncertainty using confidence intervals, scenario analysis, calibration scoring, and AI-driven ensemble methods.
7 min read7 sections
Scoring forecasts
Learn what epistemic uncertainty means in AI models, how it differs from aleatoric uncertainty, and why it matters for trustworthy, transparent AI systems.
7 min read8 sections
Scoring forecasts
Calibration measures whether your stated confidence matches reality. Learn what it means in forecasting, why it matters in markets, and how to improve it.
8 min read10 sections
Scoring forecasts
Learn how to evaluate a forecasting model — from error metrics and backtesting to overfitting, calibration, and transparency. A practical framework.
8 min read9 sections
Scoring forecasts
Learn how forecasters measure accuracy using MAE, RMSE, Brier scores, and calibration. A clear, practical guide for thinking critically about predictions.
7 min read9 sections
Scoring forecasts
Learn what a Brier score is, how it's calculated, and why it's the gold standard for evaluating probabilistic predictions in AI and markets.
7 min read9 sections
Scoring forecasts
Learn what confidence intervals mean in forecasting, why they matter in financial markets, and how understanding uncertainty makes you a sharper analyst.
1 min read1 section
