Why is standard k-fold cross-validation inappropriate for time series data?
- A Random splits let the model train on future data and predict the past
- B Time series data cannot be split
- C It requires too much memory
- D Folds must be equal in size
Answer
Random splits let the model train on future data and predict the past
Forward-chaining validation trains on everything before a cutoff and validates after it, which reflects how the model will actually be used.





