{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:56:38Z","timestamp":1790610998811,"version":"4.1.0"},"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>This paper studies a public-data U.S.-equity research pipeline in which security identity, filing availability, source transitions, transaction costs, and temporal validation are specified before performance is interpreted. The released sample screens 822 securities and admits 487 equities. It contains 715,447 daily market observations and 37,273 point-in-time fundamental observations. Forty-seven of 48 factor definitions are estimable. Five asset-pricing families show higher mean in-sample adjusted R-squared for multifactor specifications (0.259\u20130.301) than for CAPM (0.063). Eight long-only portfolio methods are evaluated under ex-ante one-way costs of 5, 10, and 20 basis points over a 32-month factor-portfolio window. Eight prediction models are assessed in 17 purged monthly test folds using two characteristics. Every non-constant model\u2019s bootstrap interval for mean rank correlation includes zero, and stable after-cost incremental value is not established. The contribution is a connected empirical design that preserves negative and inconclusive findings while making the sample\u2019s public-data and short-window limitations explicit.<\/jats:p>","DOI":"10.2139\/ssrn.7528419","type":"posted-content","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:48:08Z","timestamp":1790606888000},"source":"Crossref","is-referenced-by-count":0,"title":["An Auditable Public-Data U.S. Equity Research Pipeline: Point-in-Time Factors, Asset Pricing, Portfolio Construction, and Walk-Forward Machine Learning"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1987-1699","authenticated-orcid":true,"given":"Amit Kumar","family":"Dudi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:17:48Z","timestamp":1790608668000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7528419"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7528419","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}