Time series: the lie of the random split
Same data, same model, two different splits. One says "almost perfect", the other says "worse than the mean". Which one is true?
4 steps
210 XP
A free account is needed
Start the lesson →
Sources
- Bergmeir, C. & Benítez, J. 2012 · On the Use of Cross-Validation for Time Series Predictor Evaluation · Information Sciences, 191
- Hyndman, R. & Athanasopoulos, G. 2021 · Forecasting: Principles and Practice (3. baskı) · OTexts
- Kapoor, S. & Narayanan, A. 2023 · Leakage and the Reproducibility Crisis in ML-based Science · Patterns, 4(9)
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons