Forecast Collapse in Time-Series Foundation Models

• URL: http://arxiv.org/abs/2608.14106v1
• Date: Fri, 14 Aug 2026 09:08:02 GMT
• Title: Forecast Collapse in Time-Series Foundation Models
• Abstract summary: We investigate forecast collapse across time-series foundation models (TSFMs), twelve deep-learning forecasting models, and 97 public benchmark configurations.<n>We find that low predictability limits the amplitude of calibrated point forecasts, while per-series objectives leave cross-series structure unidentified.<n>To address this tradeoff, we introduce CalibRank, a simple objective that balances calibration and ranking.
• Score: 35.06550187645666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-sectional correlation. We call this forecast collapse. Surprisingly, the phenomenon largely disappears when forecasting trading volume under the same setting. We investigate forecast collapse across time-series foundation models (TSFMs), twelve deep-learning forecasting models, and 97 public benchmark configurations, and find that it is closely tied to target predictability. We identify two distinct reasons behind it: low predictability limits the amplitude of calibrated point forecasts, while per-series objectives leave cross-series structure unidentified. These findings reveal a calibration-ranking tradeoff: optimizing squared error leads to flat predictions, whereas directly optimizing cross-sectional correlation improves ranking but can inflate forecast amplitude by more than an order of magnitude. To address this tradeoff, we introduce CalibRank, a simple objective that balances calibration and ranking. On Finance1K, CalibRank nearly triples cross-sectional correlation while keeping amplitude close to the target, and improves correlation on all tested models. Our results reveal a blind spot in conventional time-series evaluation: per-series metrics can hide failures in cross-series structure needed by downstream decisions.

Related papers

• Adaptive Multi-Scale Forecasting and Gate-Localized Conformal Prediction for Multivariate Nonstationary Time Series [7.704601239153111]
  ABF-T-GLCP is a model-agnostic framework for forecasting and uncertainty quantification in nonstationary time series.<n>The forecasting module combines horizon-specific temporal experts through a learned gate and refines predictions using sparse predictive transfer.<n>The uncertainty module, Gate-Localized Conformal Prediction, uses the learned gate state, together with temporal recency, to select locally relevant calibration residuals.
  arXiv  Detail & Related papers  (2026-07-25T11:46:38Z)
• Asymmetric Peak-Aware Loss for Peak-Critical Time Series Forecasting [1.7126708168238123]
  In operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction.<n>We introduce Asymmetric Peak-Aware Loss (APAL), a model-agnostic objective that penalizes under-predictions more heavily and increases the training weight of peak regions within each forecast window.<n>APAL improves tail accuracy and peak-prediction quality while exposing a controllable trade-off with aggregate error, making it a practical solution when peak-prediction failures are the dominant operational concern.
  arXiv  Detail & Related papers  (2026-07-16T11:44:48Z)
• Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most [11.4807141145402]
  In inverse scaling, more capable models produce worse distributional forecasts on forecasting problems with superlinear growth and tail risk of regime change.<n>The pattern appears on ForecastBench-Sim, in forecasting synthetic SIR epidemics with a matched linear control, and replicates in real-world datasets on COVID-19, measles, housing markets, and hyperinflation.<n>This inverse scaling does not appear on single-threshold metrics common in LLM forecasting benchmarks, reversing the sign of the capability--accuracy relationship on identical outputs.
  arXiv  Detail & Related papers  (2026-05-21T16:14:33Z)
• Forecasting the U.S. Treasury Yield Curve: A Distributionally Robust Machine Learning Approach [0.12891210250935145]
  We study U.S. Treasury yield curve forecasting under distributional uncertainty.<n>Rather than minimizing average forecast error, the forecaster selects a decision rule that minimizes worst case expected loss.<n>We propose a distributionally robust ensemble forecasting framework that integrates factor models with high dimensional nonparametric machine learning models.
  arXiv  Detail & Related papers  (2026-01-08T05:26:43Z)
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment [92.70019102733453]
  Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence.<n>We propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions.
  arXiv  Detail & Related papers  (2025-10-28T16:09:59Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• Consistency Checks for Language Model Forecasters [54.62507816753479]
  We measure the performance of forecasters in terms of the consistency of their predictions on different logically-related questions.<n>We build an automated evaluation system that generates a set of base questions, instantiates consistency checks from these questions, elicits predictions of the forecaster, and measures the consistency of the predictions.
  arXiv  Detail & Related papers  (2024-12-24T16:51:35Z)
• Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting [65.40983982856056]
  We introduce STOIC, that leverages correlations between time-series to learn underlying structure between time-series and to provide well-calibrated and accurate forecasts. Over a wide-range of benchmark datasets STOIC provides 16% more accurate and better-calibrated forecasts.
  arXiv  Detail & Related papers  (2024-07-02T20:14:32Z)
• Loss Shaping Constraints for Long-Term Time Series Forecasting [79.3533114027664]
  We present a Constrained Learning approach for long-term time series forecasting that respects a user-defined upper bound on the loss at each time-step. We propose a practical Primal-Dual algorithm to tackle it, and aims to demonstrate that it exhibits competitive average performance in time series benchmarks, while shaping the errors across the predicted window.
  arXiv  Detail & Related papers  (2024-02-14T18:20:44Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• All-Clear Flare Prediction Using Interval-based Time Series Classifiers [0.21028463367241026]
  An all-clear flare prediction is a type of solar flare forecasting that puts more emphasis on predicting non-flaring instances. Finding the right balance between avoiding false negatives (misses) and reducing the false positives (false alarms) is often challenging.
  arXiv  Detail & Related papers  (2021-05-03T22:40:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.