📏  Model Score

Model Score#

The raw numeric output a model assigns before thresholding.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

A model score is the continuous output a classifier assigns each example — a probability or real-valued score of belonging to the positive class — before it becomes a hard label. Logistic regression, random forests, and neural nets all emit scores.

Score vs label#

Turning a score into a decision requires a threshold — above it, positive; below, negative. The score carries more information than the label: its ranking (are positives scored above negatives?) is what threshold-free metrics like AUC measure, and its magnitude matters for ranking and prioritization.

Score vs probability#

A score need not be a calibrated probability — a score of 0.9 doesn’t guarantee a 90% chance of being positive unless the model is calibrated (e.g., via temperature or Platt scaling). Use the raw score for ranking, the calibrated one for decisions that need real probabilities.


Theme: Classification & Averaging Metrics  ·  All terminology



See also

Source article Adapted (context, re-expressed) in our own words from: Model Score (insightful-data-lab.com).

Tags: purpose: reference topic: terminology level: intermediate