{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T15:04:32Z","timestamp":1790348672886,"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 documents a two-phase research program to identify statistically defensible trading edges in foreign exchange markets. Phase I conducted an exhaustive, rule-based search for structural and fundamental factors-real yield differentials, Commitment of Traders (COT) positioning, sessionbased liquidity patterns, and inter-market correlations-explicitly excluding conventional technical indicators, and subjected 18,681 candidate strategy\/parameter combinations across 22 research phases to a four-stage validation gauntlet (in-sample\/walk-forward testing, Monte Carlo Permutation Testing, Bonferroni correction, and the Deflated Sharpe Ratio). Zero candidates passed the complete gauntlet, a null result interpreted as evidence of the pipeline's capacity to reject data-mined artifacts rather than a failure of the research program. Informed by this result and by a review of external reference material, the program subsequently evolved into Phase II: a fundamentals-driven machine learning architecture combining gradient-boosted ensemble models (LightGBM, XGBoost, Random Forest) trained on macroeconomic (FRED) and cross-asset (Yahoo Finance) data, hidden Markov model-based regime-strict filtering, walk-forward cross-validation, and a production deployment layer with explicit risk controls. This paper documents both phases, compares their methodological standards-including a materially different statistical significance threshold between phases-and outlines the audits and extensions needed before any Phase II strategy is promoted to live trading.<\/jats:p>","DOI":"10.2139\/ssrn.7456601","type":"posted-content","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T14:40:11Z","timestamp":1790347211000},"source":"Crossref","is-referenced-by-count":0,"title":["Systematic Alpha Discovery in Foreign Exchange Markets A Two-phase Research Program: From Exhaustive Structural-factor Search to Fundamentals-Driven Machine Learning"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3639-1399","authenticated-orcid":true,"given":"Azfar","family":"Bashar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T14:40:11Z","timestamp":1790347211000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7456601"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7456601","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}