Publications
Recherches sur les agents IA, backtests et audits de prévisions de marché, et architecture de la plateforme.
Évaluation des prévisions
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 de lecture7 sections
Évaluation des prévisions
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 de lecture5 sections
Évaluation des prévisions
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 de lecture8 sections
Évaluation des prévisions
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 de lecture6 sections
Évaluation des prévisions
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 de lecture4 sections
Évaluation des prévisions
A rigorous framework for comparing forecasting models without bias — covering evaluation protocols, metrics, baselines, and statistical significance tests.
7 min de lecture9 sections
Évaluation des prévisions
Learn how to measure and interpret forecast uncertainty using confidence intervals, scenario analysis, calibration scoring, and AI-driven ensemble methods.
7 min de lecture7 sections
Évaluation des prévisions
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 de lecture8 sections
Évaluation des prévisions
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 de lecture10 sections
Évaluation des prévisions
Learn how to evaluate a forecasting model — from error metrics and backtesting to overfitting, calibration, and transparency. A practical framework.
8 min de lecture9 sections
Évaluation des prévisions
Learn how forecasters measure accuracy using MAE, RMSE, Brier scores, and calibration. A clear, practical guide for thinking critically about predictions.
7 min de lecture9 sections
Évaluation des prévisions
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 de lecture9 sections
Évaluation des prévisions
Learn what confidence intervals mean in forecasting, why they matter in financial markets, and how understanding uncertainty makes you a sharper analyst.
1 min de lecture1 section
