Forecast Collapse in Time-Series Foundation Models
Quick summary
arXiv:2608.14106v1 Announce Type: cross 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.
Key takeaways
- arXiv:2608.14106v1 Announce Type: cross 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.
- 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.
Why it matters
“Forecast Collapse in Time-Series Foundation Models” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments