AI engineering glossary · Time series recsys
What is time series cross-validation?
Time series cross-validation (also called TimeSeriesSplit): A version of cross-validation where every validation block comes strictly after its training block, with training windows that expand or slide. Random splits are avoided because they let the model see the future. In scikit-learn it is TimeSeriesSplit.
Time series cross-validation: an example
TimeSeriesSplit(n_splits=5) on 600 rows gives five train/validation pairs, each later in time than the last.
Related terms
More Time series recsys terms
- Trend
- Unit root
- User-based collaborative filtering
- User-item matrix
- Vector autoregression
- Volatility clustering
- Weak stationarity
- Weighted absolute percentage error
Where you learn it
Time series cross-validation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.