{"paper_id":"2508.11856","title":"Optimal Portfolio Construction -- A Reinforcement Learning Embedded Bayesian Hierarchical Risk Parity (RL-BHRP) Approach","authors":["Shaofeng Kang","Zeying Tian"],"paper_date":"2025-08-16","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.11856v1","page_url":"https://thequant.space/flowcharts/optimal-portfolio-construction----a-reinforcement-learning-e/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a two‑level, learning‑based portfolio method called RL‑BHRP that spreads risk across sectors and stocks and adapts exposures as market conditions change.","quote":"We propose a two-level, learning-based portfolio method (RL-BHRP) that spreads risk across sectors and stocks, and adjusts exposures as market conditions change.","summary":"We propose a two-level, learning-based portfolio method (RL-BHRP) that spreads risk across sectors and stocks, and adjusts exposures as market conditions change. Using U.S. Equities from 2012 to mid-2025, we design the model using 2012 to 2019 data, and evaluate it out-of-sample from 2020 to 2025…","strategy":"RL-BHRP"},"assumptions":{"status":"available","items":[{"assumption":"Each sector has latent parameters governing its expected return and risk, which inform priors for individual stocks.","type":"model","stated":"explicit","quote":"We assume each sector has latent parameters governing its expected return and risk, which in turn inform the priors for individual stocks in that sector."},{"assumption":"Asset returns follow a Normal likelihood and covariances are estimated with Ledoit–Wolf shrinkage.","type":"statistical","stated":"explicit","quote":"The Bayesian layer uses Normal likelihoods for returns with Ledoit–Wolf shrinkage for covariances."},{"assumption":"Transaction costs are proportional with a constant cost rate c applied to absolute weight changes.","type":"execution","stated":"explicit","quote":"Trading incurs proportional cost c such that the transaction cost function for the entire trading period is defined by a linear function that Ct(c, w) = c"},{"assumption":"The data source (Yahoo Finance adjusted closes) may omit delistings and mis‑handle corporate actions, introducing survivorship risk.","type":"data","stated":"explicit","quote":"The empirical analysis relies on Yahoo Finance adjusted closes. While convenient and widely used, this source can omit delistings and occasionally mis‑handle corporate actions, which introduces survivorship risk."}]},"datasets":{"status":"available","items":[{"name":"U.S. equities (adjusted close prices)","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2012-2025","universe":"U.S. equities screened quarterly","quote":"Using U.S. equities from 2012 to mid-2025, we design the model using 2012–2019 data and evaluate it out-of-sample from 2020 to 2025","known_id":"yahoo-finance"},{"name":"Sector index built from exchange‑traded funds","provider":null,"kind":"benchmark","access":"public","period":"2012-2025","universe":"Sector ETFs","quote":"evaluate it out-of-sample from 2020 to 2025 against a sector index built from exchange‑traded funds"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"We obtain adjusted close (total-return) prices from Yahoo Finance from January 1, 2012, to August 13, 2025.","mentions":2,"used_in":1}],"sample":{"start":"2020-02","end":"2025-08","market":"U.S. equities","asset_class":"equities","frequency":"monthly"},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Proportional cost c applied to absolute weight changes; a 5 bps one‑way cost model is used for turnover calculations.","quote":"Trading incurs proportional cost c such that the transaction cost function for the entire trading period is defined by a linear function that Ct(c, w) = c","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Proportional cost c applied to absolute weight changes; a 5 bps one‑way cost model is used for turnover calculations.","card_quote":"Trading incurs proportional cost c such that the transaction cost function for the entire trading period is defined by a linear function that Ct(c, w) = c","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Over the out‑of‑sample test window the RL‑BHRP portfolio achieved a total cumulative return of 119.96% (CAGR 15.16%) versus 101.37% (CAGR 13.36%) for the static BHRP comparator and 91.41% (CAGR 12.33%) for the sector benchmark.","kind":"performance","quote":"Total Cumulative Return 1.199612 ... 1.013672 ... 0.914063 ... CAGR (Geometric Ann.) 0.151637 ... 0.133563 ... 0.123310"},{"finding":"RL‑BHRP attained a Sharpe ratio of 0.9048, higher than the static BHRP (0.8461) and the benchmark (0.7630).","kind":"performance","quote":"Sharpe 0.904829 ... 0.846076 ... 0.763042"},{"finding":"Maximum drawdown for RL‑BHRP was –20.33%, modestly larger than the benchmark’s –18.32% but comparable to the static comparator.","kind":"performance","quote":"Max Drawdown -0.203308 ... -0.191023 ... -0.183210"},{"finding":"Tracking error of RL‑BHRP relative to the benchmark was low (3.69%), indicating limited active risk.","kind":"performance","quote":"Tracking Error 0.036883 ... 0.035790 ... 0.000000"},{"finding":"VaR 5% and CVaR 5% for RL‑BHRP were –7.41% and –10.24%, respectively, lying between the static BHRP and the benchmark.","kind":"performance","quote":"VaR 5% (period) -0.074066 ... -0.067241 ... -0.079989 ... CVaR 5% (period) -0.102409 ... -0.097049 ... -0.103351"}],"reported_performance":{"strategy":"RL-BHRP","sharpe":0.9048,"sharpe_benchmark":0.763,"annual_return_pct":15.1637,"total_return_pct":119.9612,"max_drawdown_pct":20.3308},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":44,"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":"2026-11-14T17:29:46Z"},"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/"}