{"paper_id":"2511.21221","title":"Portfolio Optimization via Transfer Learning","authors":["Kexin Wang","Xiaomeng Zhang","Xinyu Zhang"],"paper_date":"2025-11-26","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.21221v1","page_url":"https://thequant.space/flowcharts/portfolio-optimization-via-transfer-learning/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a transfer learning based portfolio strategy that leverages cross‑market information to improve target market performance.","quote":"we develop a portfolio strategy based on transfer learning that leverages cross‑market information to enhance the investment performance in the market of interest by forward validation.","summary":"Recognizing that asset markets generally exhibit shared informational characteristics, we develop a portfolio strategy based on transfer learning that leverages cross-market information to enhance the investment performance in the market of interest by forward validation. Our strategy…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"There exist constants and parameter sequences such that d^{ζ}h^{-1/2}=o(1) and certain convergence rates hold for estimated means and covariances.","type":"statistical","stated":"explicit","quote":"... (i) dζh−1 2 = o(1); (ii) h 1 2d−ζ ∥bµm,τi −µ∗ m,τi ∥2= Op(1) and h 1 2d−ζ ∥bΣm,τi −Σ∗ m,τi ∥F= Op(1); (iii) h 1 2d−ζ ∥µ∗ m,τi+1 −µ∗ m,τi ∥2= O(1) and h 1 2d−ζ ∥Σ∗ m,τi+1 −Σ∗ m,τi ∥F= O(1)."},{"assumption":"The target mean and covariance estimators converge at rate h^{1/2}d^{-ζ}.","type":"statistical","stated":"explicit","quote":"Assumption 3. (i) h 1 2d−ζ ∥µ0,τi −µ∗ 0,τi ∥2= O(1); (ii) h 1 2d−ζ ∥Σ0,τi −Σ∗ 0,τi ∥F= O(1)."}]},"datasets":{"status":"available","items":[{"name":"dual‑listed A‑shares and H‑shares portfolio","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"stocks dual‑listed in A‑shares and H‑shares","quote":"case studies of two portfolios: one consisting of stocks dual‑listed in A‑shares and H‑shares, and another comprising equities from various industries of the United States."},{"name":"U.S. equities portfolio","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"equities from various industries of the United States","quote":"... another comprising equities from various industries of the United States."}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"The three factors required (MKT, SMB, HML) are obtained from the CRSP database for the period from January 2021 to December 2023.","mentions":2,"used_in":2},{"id":"compustat","name":"Compustat","provider":"S&P Global","kind":"fundamentals","access":"commercial","quote":"The data information comes from Osiris, CRSP and Compustat database.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The proposed TL strategy automatically excludes uninformative source datasets and asymptotically concentrates weights on informative ones.","kind":"theoretical","quote":"Our strategy automatically excludes uninformative and misleading source datasets, asymptotically concentrating portfolio weights on the informative datasets..."},{"finding":"The TL strategy asymptotically achieves the maximum attainable Sharpe ratio, with lower variance than the non‑transfer baseline when informative sources exist.","kind":"theoretical","quote":"... the variance of the Sharpe ratio under our strategy is asymptotically lower than that of the Non−transfer baseline strategy"},{"finding":"Numerical studies and case studies demonstrate promising performance of the TL strategy.","kind":"performance","quote":"The promising performance is demonstrated by numerical studies and case studies of two portfolios..."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:20:47Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}