{"paper_id":"2312.05169","title":"Onflow: an online portfolio allocation algorithm","authors":["Gabriel Turinici","Pierre Brugiere"],"paper_date":"2023-12-08","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2312.05169v1","page_url":"https://thequant.space/flowcharts/onflow-an-online-portfolio-allocation-algorithm/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes Onflow, a reinforcement‑learning portfolio allocation algorithm based on gradient flows and a softmax parameterisation.","quote":"We introduce Onflow, a reinforcement learning method for optimizing portfolio allocation via gradient flows.","summary":"We introduce Onflow, a reinforcement learning technique that enables online optimization of portfolio allocation policies based on gradient flows. We devise dynamic allocations of an investment portfolio to maximize its expected log return while taking into account transaction fees. The portfolio…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Zero transaction costs (ξ = 0) in the theoretical convergence analysis.","type":"execution","stated":"explicit","quote":"Proposition 1 assumes zero transaction costs."},{"assumption":"Asset dynamics are log‑normal in the continuous‑time limit.","type":"model","stated":"explicit","quote":"we will consider the continuous limit i.e., T = R+, no transaction fees (ξ = 0) and assume that the asset dynamic is log-normal."},{"assumption":"No short selling; portfolio weights are positive and sum to one.","type":"market","stated":"explicit","quote":"We suppose that each π(k) is positive, i.e., no short selling is allowed."},{"assumption":"Softmax parameterisation of the portfolio ensures all weights are positive.","type":"model","stated":"explicit","quote":"The portfolio allocation is parameterized through a softmax function."},{"assumption":"Transaction costs are small relative to other ODE terms and can be treated as a perturbation.","type":"execution","stated":"explicit","quote":"such costs exist but are typically an order of magnitude smaller than the other terms in the ODE; they can therefore be incorporated through a perturbation analysis"},{"assumption":"The ODE solver (odeint) default settings are sufficient for implementation.","type":"other","stated":"implied","quote":"The ODE resolution is very robust with respect to the method used; in practice we employed the odeint routine from the SciPy Python package"}]},"datasets":{"status":"available","items":[{"name":"Old NYSE","provider":null,"kind":"market-prices","access":"public","period":"1965-1987","universe":"36 NYSE stocks","quote":"For the numerical tests we use the ”Old NYSE” database, a benchmark from the literature listing the prices of 36 stocks quoted on the New York Stock Exchange from 1965 to 1987 (5651 daily prices i.e., T = 5650)"},{"name":"High‑volatility tech stocks (NVDA, TSLA)","provider":null,"kind":"market-prices","access":"public","period":"2020-2025","universe":"NVDA and TSLA","quote":"we considered two cryptocurrencies : the Bitcoin (BTC-USD ticker) and Ethereum (ETH-USD) and two impactful tech stocks Nvidia (NVDA), Tesla (TSLA). The dataset is constructed with end of day quotes for the period Jan 1st 2020 to Nov 28th 2025."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A flat fee level ξ is used (e.g., ξ = 2%); results are reported with and without this fee.","quote":"the … fee level ξ, specify the parameter τ and solve ODE (11).","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat fee level ξ is used (e.g., ξ = 2%); results are reported with and without this fee.","card_quote":"the … fee level ξ, specify the parameter τ and solve ODE (11).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Onflow replicates the Markowitz optimal portfolio for log‑normal assets with zero transaction costs.","kind":"theoretical","quote":"For log-normal assets with zero transaction costs, Onflow replicates Markowitz optimal portfolio, achieving the best possible allocation."},{"finding":"With zero transaction costs, Onflow’s performance is comparable to Cover’s Universal Portfolio and Helmbold et al.’s multiplicative updates.","kind":"performance","quote":"a) comparable to benchmark strategies such as Cover's Universal Portfolio or Helmbold et al. “multiplicative updates” approach when transaction costs are zero"},{"finding":"When transaction costs are high (e.g., ξ = 2%), Onflow outperforms previous procedures.","kind":"performance","quote":"b) better than previous procedures when transaction costs are high."},{"finding":"On high‑volatility assets, Onflow achieves Sharpe ratios of 1.21 (vs 1.19 for EG) for tech stocks and 0.86 (vs 0.82 for EG) for cryptocurrencies.","kind":"performance","quote":"Sharpe ratio for ’Onflow’ is 0.86, for ’EG’ 0.82, for ’BTC-USD’ 0.83 and for ’ETH-USD’ 0.87."},{"finding":"Across 1000 random 10‑asset samples, Onflow’s Sharpe ratio is statistically superior (p‑value < 10⁻³) to EG, uniform CRP and Split‑and‑Forget.","kind":"performance","quote":"a standard Wilcoxon test reveals that the Sharpe ratio of ’Onflow’ is superior to each of the other strategies and this difference is statistically significant (p-value < 10−3)."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":30,"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":"2026-11-14T18:18:12Z"},"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/"}