{"paper_id":"2510.14986","title":"RegimeFolio: A Regime Aware ML System for Sectoral Portfolio Optimization in Dynamic Markets","authors":["Yiyao Zhang","Diksha Goel","Hussain Ahmad","Claudia Szabo"],"paper_date":"2025-09-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.14986v1","page_url":"https://thequant.space/flowcharts/regimefolio-a-regime-aware-ml-system-for-sectoral-portfolio/","scores":{"empirical_rigor":6,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes RegimeFolio, a novel regime‑aware and sector‑specialized framework that integrates volatility regime segmentation, sector‑specific ensemble forecasting, and adaptive mean‑variance allocation.","quote":"To address these challenges, we propose RegimeFolio, a novel regime-aware and sector-specialized framework that, unlike existing regime-agnostic models (e.g., DeepVol, DRL optimizers), integrates explicit volatility regime segmentation with sector-specific ensemble forecasting and adaptive mean‑variance allocation.","summary":"Financial markets are inherently non-stationary, with shifting volatility regimes that alter asset co-movements and return distributions. Standard portfolio optimization methods, typically built on stationarity or regime-agnostic assumptions, struggle to adapt to such changes. To address these…","strategy":"RegimeFolio"},"assumptions":{"status":"available","items":[{"assumption":"Market volatility regimes can be identified using the CBOE VIX and a rolling‑tercile methodology.","type":"market","stated":"explicit","quote":"Market volatility regimes are classified using the CBOE VIX as the primary segmentation criterion."},{"assumption":"Within each identified regime, asset return dynamics are locally stationary.","type":"statistical","stated":"explicit","quote":"The modeling assumes local stationarity within regimes, which may not hold during abrupt structural breaks."},{"assumption":"The investment universe consists of the historical constituents of the S&P 500, using point‑in‑time CRSP membership to avoid survivorship bias.","type":"data","stated":"explicit","quote":"Our investment universe is based on the historical constituents of the S&P 500 index[42] to avoid survivorship bias. We use a point in time database from CRSP that provides the exact list of index members for any given date in our study period (2020 – 2024)."},{"assumption":"Transaction costs are represented only by fixed per‑trade fees, ignoring price impact, slippage, and liquidity constraints.","type":"execution","stated":"explicit","quote":"Finally, transaction cost modeling includes fixed per trade costs but omits price impact, slippage, and liquidity constraints."},{"assumption":"Sector‑specific ensemble models (Random Forest, Gradient Boosting) trained separately for each regime capture conditional return structures.","type":"model","stated":"explicit","quote":"sector-specific ensemble forecasting models trained separately for each regime"}]},"datasets":{"status":"available","items":[{"name":"CRSP daily stock file","provider":"CRSP","kind":"market-prices","access":"commercial","period":"2020-2024","universe":"34 large cap U.S. equities (S&P 500 constituents)","quote":"The dataset comprises 34 carefully selected large cap U.S. equities distributed across 7 major economic sectors.","known_id":"crsp"},{"name":"CBOE VIX","provider":"Chicago Board Options Exchange","kind":"options","access":"public","period":"2020-2024","universe":null,"quote":"Historical VIX data is obtained from the Chicago Board Options Exchange, providing daily volatility expectations derived from S&P 500 index options.","known_id":"cboe"}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"We use a point in time database from CRSP that provides the exact list of index members for any given date in our study period (2020 – 2024).","mentions":1,"used_in":1}],"sample":{"start":"2020","end":"2024","market":"34 large cap U.S. equities","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":false,"detail":"fixed per trade costs but omits price impact, slippage, and liquidity constraints","quote":"Finally, transaction cost modeling includes fixed per trade costs but omits price impact, slippage, and liquidity constraints.","source":"front_matter","rule":"R3","candidates":{"front_matter":"partial","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"fixed per trade costs but omits price impact, slippage, and liquidity constraints","card_quote":"Finally, transaction cost modeling includes fixed per trade costs but omits price impact, slippage, and liquidity constraints.","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"RegimeFolio achieved a cumulative return of 137.0% versus 73.8% for the S&P 500 benchmark.","kind":"performance","quote":"the regime-aware portfolio achieved a 137.0% cumulative return versus 73.8% for the S&P 500 benchmark (Table VII)"},{"finding":"The strategy delivered a Sharpe ratio of 1.17 and a 12% lower maximum drawdown compared to the benchmark.","kind":"performance","quote":"The framework achieves a cumulative return of 137 percent, a Sharpe ratio of 1.17, a 12 percent lower maximum drawdown"},{"finding":"Forecast accuracy improved by 15–20% (MAE reduction) relative to linear baselines, especially in cyclical sectors.","kind":"predictive-accuracy","quote":"Ensemble models (Random Forest, Gradient Boosting) outperform linear baselines by 15–20% in MAE reduction, with larger gains in cyclical sectors such as Energy and Financials"},{"finding":"The strategy outperformed the S&P 500 benchmark by 63.2% over the 5‑year period, generating $63.2 million on a $100 million mandate.","kind":"performance","quote":"The 63.2% outperformance over the S&P 500 benchmark translates to substantial economic value creation: on a $100 million institutional mandate, the strategy generates $63.2 million in additional returns over the 5 year period"},{"finding":"Maximum drawdown was reduced by 12.0 percentage points (‑29.3% vs ‑41.2%).","kind":"performance","quote":"The 12.0 percentage point reduction in maximum drawdown (-29.3% vs -41.2%) provides substantial downside protection during market stress periods."}],"reported_performance":{"strategy":"RegimeFolio","sharpe":1.17,"sharpe_benchmark":0.66,"annual_return_pct":18.9,"total_return_pct":137,"max_drawdown_pct":29.3},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":61,"citations":{"cited_by_in_corpus":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"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":"2026-11-14T17:27:14Z"},"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/"}