Data & Analytics
(R² (Bestimmtheitsmaß))R-Squared (Coefficient of Determination)
Also known as:
R-Squared
Coefficient of Determination
R2 Score
Updated: 2/12/2026
The proportion of variance in the target variable explained by the model (0-1).
Quick Summary
R² shows how much variance a model explains (0-1) – the most intuitive regression metric.
Explanation
R² = 1 - (SS_res / SS_tot). R²=0.85 means 85% of variance explained. Can be negative.
Marketing Relevance
R² is the most intuitive regression metric for stakeholder communication.
Common Pitfalls
R² always increases with more features (use adjusted R²). High R² ≠ causation.
Origin & History
R² was introduced by Sewall Wright (1921) and is ubiquitous in statistics.
Comparisons & Differences
R-Squared (Coefficient of Determination) vs. Adjusted R²
Standard R² always increases with more features; Adjusted R² penalizes overparameterization.