Metraipolis › archive › dc_ae5ed7dac975

Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target — arXiv:2609.26303

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26303
License (as archived)
CC0-1.0
Archived
2026-10-08T15:11:29.809Z
SHA-256 of the archived text
a34e0fe648f48e42e2b665b7a13a9f347015f6af4ce1a4f74406fa644c253175
Stable URL of this page
https://metraipolis.com/documento/dc_ae5ed7dac975

How to cite

Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target — arXiv:2609.26303 — arXiv (en), https://arxiv.org/abs/2609.26303 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae5ed7dac975 (Metraipolis archive dc_ae5ed7dac975, sha256 a34e0fe648f48e42e2b665b7a13a9f347015f6af4ce1a4f74406fa644c253175)
BibTeX
@misc{dcae5ed7dac975,
  title = {Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target — arXiv:2609.26303},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26303},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae5ed7dac975; sha256 a34e0fe648f48e42e2b665b7a13a9f347015f6af4ce1a4f74406fa644c253175},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26303. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Forecasters often score the same units per date against one standardized realized outcome. We show that every standardized forecast splits exactly into a component aligned with this common target and a component uncorrelated with it. Three consequences follow: forecast-error correlation largely mirrors forecast correlation and is therefore a poor measure of diversity; an equally weighted combination beats a no-information forecast only when average alignment is large relative to the combination's dispersion; and the gain from adding a forecaster separates into genuine improvement and mere dilution, which equal-weight admission can mistakenly reward. We develop a cautious selection rule, study it in simulations, and apply it to language-model forecasts of US equity rankings and mechanical signals ranking exchange-traded funds. Selection removes most dilution losses, but no combination beats the no-information forecast.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Econometrics (econ.EM) ; Machine Learning (cs.LG); Statistical Finance (q-fin.ST); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2609.26303 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T14:37:29.566Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).