# Spectral Predictability as a Fast Reliability Indicator for Time Series Forecasting Model Selection

arXiv: https://arxiv.org/abs/2511.08884 · HTML: https://mlsanity.com/paper/2511.08884/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2025.

## Built on by (most cited first, 3 of 3)

- [FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models](https://mlsanity.com/paper/2604.16448/) (2026)
- [Preliminary Insights in Chronos Frequency Data Understanding and Reconstruction](https://mlsanity.com/paper/2605.06361/) (2026)
- [The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting](https://mlsanity.com/paper/2607.13006/) (2026)

## Abstract (arXiv)

Practitioners deploying time series forecasting models face a dilemma: exhaustively validating dozens of models is computationally prohibitive, yet choosing the wrong model risks poor performance. We show that spectral predictability~Omega -- a simple signal processing metric -- systematically stratifies model family performance, enabling fast model selection. We conduct controlled experiments in four different domains, then further expand our analysis to 51 models and 28 datasets from the GIFT-Eval benchmark. We find that large time series foundation models (TSFMs) systematically outperform lightweight task-trained baselines when Omega is high, while their advantage vanishes as Omega drops. Computing Omega takes seconds per dataset, enabling practitioners to quickly assess whether their data suits TSFM approaches or whether simpler, cheaper models suffice. We demonstrate that Omega stratifies model performance predictably, offering a practical first-pass filter that reduces validation costs while highlighting the need for models that excel on genuinely difficult (low-Omega) problems rather than merely optimizing easy ones.