{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:51:16Z","timestamp":1791395476409,"version":"4.3.3"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":0,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>The paper proposes a functional forecasting framework for the next-day path of spot betas. We reconstruct spot betas from asynchronously sampled transaction prices using Fourier estimators of spot covariance and variance. Motivated by the empirical features of spot beta estimates, we employ robust dynamic functional principal component analysis for dimension reduction and forecast the resulting scores using autoregressive models, residual networks and cross-sectional elastic pooling. Using 30 largecap NASDAQ-listed stocks over 2022-2024, we find that score-based models outperform forecasting benchmarks, including functional autoregression. Pooling improves upon stock-specific autoregressive models, while adding a residual network under full pooling yields no significant further gain. By contrast, elastic pooling significantly outperforms the fully pooled autoregression, both with and without residual network augmentation. As a complementary contribution, we derive a stable central limit theorem for the spot beta estimator employed and a feasible closed-form rule for selecting the Fourier cutoff frequencies, thereby providing a fully operational procedure for obtaining the spot beta estimates that feed the forecasting exercise.<\/jats:p>","DOI":"10.2139\/ssrn.7570098","type":"posted-content","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:58:48Z","timestamp":1791392328000},"source":"Crossref","is-referenced-by-count":0,"title":["Functional Forecasting of Intraday Spot Beta Paths"],"prefix":"10.2139","author":[{"given":"Paolo","family":"Cinque","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2335-5619","authenticated-orcid":true,"given":"Simona","family":"Sanfelici","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Toscano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:58:48Z","timestamp":1791392328000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7570098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7570098","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}