{"paper_id":"2501.15793","title":"Advancing Portfolio Optimization: Adaptive Minimum-Variance Portfolios and Minimum Risk Rate Frameworks","authors":["Ayush Jha","Abootaleb Shirvani","Ali Jaffri","Svetlozar T. Rachev","Frank J. Fabozzi"],"paper_date":"2025-01-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2501.15793v1","page_url":"https://thequant.space/flowcharts/advancing-portfolio-optimization-adaptive-minimum-variance/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper introduces the Adaptive Minimum-Variance Portfolio (AMVP) framework and the Adaptive Minimum-Risk Rate (AMRR) metric for dynamic portfolio optimization.","quote":"This study presents the Adaptive Minimum-Variance Portfolio (AMVP) framework and the Adaptive Minimum-Risk Rate (AMRR) metric, innovative tools designed to optimize portfolios dynamically in volatile and nonstationary financial markets.","summary":"This study presents the Adaptive Minimum-Variance Portfolio (AMVP) framework and the Adaptive Minimum-Risk Rate (AMRR) metric, innovative tools designed to optimize portfolios dynamically in volatile and nonstationary financial markets. Unlike traditional minimum-variance approaches, the AMVP…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Asset returns are computed as arithmetic returns.","type":"model","stated":"explicit","quote":"We compute arithmetic returns for both asset classes, as arithmetic returns enable straightforward aggregation of portfolio returns using linear weights and align well with mean-variance or minimum-variance optimization models."},{"assumption":"Historical covariances and volatilities are used as inputs for the initial minimum‑variance optimization.","type":"statistical","stated":"explicit","quote":"On the historical, or backward‑looking, front, we perform a minimum‑variance optimization directly on the historical returns of each asset in both portfolios, relying on the assumption that historical covariances and volatil‑ities provide an…"},{"assumption":"Closing prices are unadjusted for dividends.","type":"data","stated":"explicit","quote":"We use unadjusted closing prices for equities as reported by Bloomberg prior to the ex‑dividend date at the end of the fourth quarter, meaning our price series do not incorporate the downward price adjustments that typically follow dividend payouts."},{"assumption":"Synthetic assets can be iteratively added to improve variance estimates.","type":"model","stated":"explicit","quote":"To refine the variance further, we introduce an iterative scheme that expands the investable universe with synthetic assets derived from each MVP solution."},{"assumption":"Trading occurs at daily closing prices with no slippage or market impact.","type":"execution","stated":"implied","quote":"We compute arithmetic returns for both asset classes, as arithmetic returns enable straightforward aggregation of portfolio returns using linear weights..."}]},"datasets":{"status":"available","items":[{"name":"Dow Jones Industrial Average (DJIA) constituents","provider":"Bloomberg Terminal","kind":"market-prices","access":"commercial","period":"23 Nov 2020 – 18 Nov 2024","universe":"30 DJIA stocks","quote":"We construct two distinct portfolios for our analysis: one comprising the 30 constituents of the Dow Jones Industrial Average (DJIA)","known_id":"bloomberg"},{"name":"Major cryptocurrencies","provider":"Bloomberg Terminal","kind":"market-prices","access":"commercial","period":"19 Nov 2020 – 17 Nov 2024","universe":"30 cryptocurrencies by market cap","quote":"... the cryptocurrency portfolio extends from 19 November 2020 through 17 November 2024","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"All data were retrieved from Bloomberg Terminal on 20 November 2024, and the DJIA composition reflects the 4 constituents as of that date.","mentions":4,"used_in":3}],"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":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The AMVP framework achieves lower portfolio variance and improved diversification compared to traditional static minimum‑variance portfolios.","kind":"performance","quote":"Plotting these frontiers across successive iterations visually demonstrates an inward shift, signifying improved diversification and reduced variance for comparable return levels."},{"finding":"The Adaptive Minimum‑Risk Rate (AMRR) exhibits strong volatility persistence for DJIA (H = 1.3668) and weaker but present long‑memory for cryptocurrencies (H = 0.8651).","kind":"statistical","quote":"For the DJIA AMRR, H = 1.3668 confirms pronounced volatility persistence, whereas H = 0.8651 for cryptocurrencies aligns with weaker, yet still evident, long‑memory effects."},{"finding":"Dynamic AMRR estimates have lower Hurst exponents (DJIA H = 0.9380, Crypto H = 0.9043), indicating reduced reliance on historical patterns when forward‑looking scenarios are incorporated.","kind":"statistical","quote":"The dynamic AMRR estimates for both DJIA and cryptocurrencies have lower Hurst exponents (H = 0.9380 and H = 0.9043, respectively), in line with the reduced reliance on historically ingrained patterns once forward‑looking scenarios are incorporated."},{"finding":"The AMRR provides a shadow rate with comparable or higher expected return than Treasury bills despite lower volatility persistence.","kind":"performance","quote":"Although the AMRR exhibits lower persistence in volatility compared to Treasury bills, it achieves a comparable or sometimes higher expected return precisely because it is formed through the AMVP optimization process."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":56,"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":"2026-11-14T17:46:39Z"},"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/"}