Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance
We study this effect through a preprocessing-aware benchmark that evaluates 11 forecasting models across 16 reversible preprocessing pipelines on 29,000 M4 time series.
ProofPaper ↗
Key points
- While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current research.
- Modern benchmarks typically resort to simple scaling, failing to account for critical transformations required to address nonstationarity, such as differencing.
- This omission creates a significant structural preprocessing bias that favors models with built-in data treatments while obscuring the true potential of simpler architectures.
- Our results identify preprocessing as a key driver of forecasting performance.
Sources (1)
- [1]Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series PerformancearXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 08:50 PM
We study this effect through a preprocessing-aware benchmark that evaluates 11 forecasting models across 16 reversible preprocessing pipelines on 29,000 M4 time series.
While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current research.
Extractive summary: sentences quoted from the sources.