Training data

How it is used

You collect, label, prepare or split training data. If the training data is biased, out of date or too small, the model will be too. Often mentioned together with validation data and test data.

Example sentences

1. The training data only covers 2022, so the model has never seen a holiday season like this one.

2. We need more labelled training data for the rare complaint types.

Common collocations

• label training data
• split into training and test data
• biased training data
• training data set

Related terms

• test setA part of the data that is held back and never used in training, so that it can show at the end how well a model works on data it has not seen.
• modelA mathematical representation of a real process, built from data, that is used to explain relationships or to make predictions about new cases.
• overfittingA problem in which a model learns the training data too closely, including its noise, so it performs well on that data but poorly on new data.
• target variableThe value a model is trained to predict, such as whether a customer will churn or how much they will spend; also called the label or dependent variable.

This word in other fields

The same English word can have a different meaning in another field:

• training data · Software Engineering
• training data · Artificial Intelligence & Machine Learning

More terms: Modelling and Machine Learning

• feature
• regression
• classification
• accuracy
• precision
• recall
• cross-validation
• baseline
• feature engineering
• clustering