AI engineering glossary · ML fundamentals
What is time-series split?
Time-series split (also called Walk-forward validation, Rolling-origin evaluation): A validation scheme for data ordered in time in which the model is always trained on earlier periods and tested on later ones, never the reverse. Random shuffling would let the model see the future, so this ordered approach gives a realistic estimate of forecasting performance.
Time-series split: an example
Train on January to June, test on July; then train on January to July, test on August, and so on.
Related terms
More ML fundamentals terms
- Train-test contamination
- Training
- Training error
- Training example
- Training set
- Transfer learning
- True risk
- Underfitting
Where you learn it
Time-series split is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.