Beginner · Fundamentals

Prediction

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. The output a trained model produces when given new input data.

Technical Definition

The output a trained model produces when given new input data.

How it works

Predictions can be a class label (cat/dog), a probability distribution, a continuous number, a sequence of tokens, or an image. The quality of predictions on unseen data is the true test of a model — high accuracy on training data with poor predictions on new data signals overfitting.

Related Concepts

• Inference — Using a trained model to make predictions on new data — the deployment phase of machine learning.
• Classification — A supervised learning task where the model assigns inputs to discrete categories.
• Regression — A supervised learning task that predicts a continuous numeric value.