# Idea A weighted average ([[harmonic mean]]) of the [[precision]] and [[recall]] scores that addresses the problems with [[accuracy]] scores. It ranges from 0 to 1, with 1 being the best F1 score. $ F_{\beta} = (1 + \beta^2) \cdot \frac{precision \cdot recall}{\left( \beta^2 \cdot precision \right) + recall} $ When $\beta = 0.5$, we place more emphasis on precision. It's called the $F_{0.5}$ score or F-score for simplicity. When $\beta = 1$, the equation reduces to the following: $ F_{\beta} = 2 \cdot \frac{precision \cdot recall}{precision + recall} $ The above equation is also known as the [[harmonic mean]] of precision and recall. ![[20240111173839.png]] # References - [Trading off precision and recall - Advice for applying machine learning | Coursera](https://www.coursera.org/learn/advanced-learning-algorithms/lecture/42TEG/trading-off-precision-and-recall)