Okuzeka
Artificial Intelligence & Machine Learning vocabulary · Data and Features

Data leakage

Meaning in artificial intelligence & machine learning, with examples

nounCommon term

In artificial intelligence & machine learning, data leakage means: A mistake in which information that won't be available at prediction time, such as test examples or future data, gets into training and makes results look better than they are.

In Turkish: veri sızıntısı

How it is used

A classic reason why a model looks excellent in testing and then fails in production. Common causes are duplicates across splits, features that contain the answer, and random splits on time-based data. Also called target leakage or test set contamination.

Example sentences

  1. 99% accuracy on day one usually means data leakage, not a great model.

  2. We found data leakage: the 'refund date' feature only exists after a customer complains.

Common collocations

  • check for data leakage
  • cause data leakage
  • target leakage
  • test set contamination
  • test setA part of the data kept aside and used only at the end, to measure how well a finished model works on examples it has never seen.
  • training dataThe examples a model learns from during training. Their quality, size and variety largely decide how well the model works on new data.
  • featureOne measurable piece of information given to a model as input, for example a customer's age, the number of past orders or the brightness of a pixel.
  • benchmarkA standard set of tasks and data used to measure models in the same way, so that results from different teams can be compared fairly.

This word in other fields

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

More terms: Data and Features

Practise with graded reading

Reading at the right level is the fastest way to make new words stick. Pick free English books by level: