Feature store

How it is used

Used by teams sharing features across models. Storage alone does not guarantee correct event times or consistent transformations.

Example sentences

1. The feature store supplies the same account-age calculation to three different models.

   Shared feature definitions reduce repeated implementations of the same input.

2. We queried historical values from the feature store to avoid using future information in training.

   Training needs the values available at the relevant past time, not today's updated values.

Common collocations

• online feature store
• feature store lookup

Related terms

• feature engineeringThe work of creating new input variables from raw data to help a model learn, for example turning a date of birth into an age or counting a customer's purchases.
• data leakageA 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.

More terms: Machine Learning and Data Processing

• artificial intelligence
• machine learning
• model
• dataset
• training data
• label
• train
• supervised learning
• neural network
• deep learning
• loss function
• overfitting