{"paper_id":"2506.19715","title":"Neural Functionally Generated Portfolios","authors":["Michael Monoyios","Olivia Pricilia"],"paper_date":"2025-06-24","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2506.19715v1","page_url":"https://thequant.space/flowcharts/neural-functionally-generated-portfolios/","scores":{"empirical_rigor":4,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a neural-network-based approach to learn the generating function of a functionally generated portfolio directly from data.","quote":"We introduce a novel neural-network-based approach to learning the generating function G(·) of a functionally generated portfolio (FGP) from synthetic or real market data.","summary":"We introduce a novel neural-network-based approach to learning the generating function G(·) of a functionally generated portfolio (FGP) from synthetic or real market data. In the neural network setting, the generating function is represented as G_θ(·), where θ is an iterable neural network…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The market satisfies the no unbounded profit with bounded risk (NUPBR) condition.","type":"market","stated":"explicit","quote":"SPT operates under a weaker assumption: no unbounded profit with bounded risk (NUPBR), which is equivalent to the existence of a non-empty set of local martingale deflators (LMDs)."},{"assumption":"Portfolio wealth processes are non‑negative for all times.","type":"model","stated":"explicit","quote":"We assume the admissibility condition P (V w,π(t) ≥0, ∀t ∈[0, T]) = 1."},{"assumption":"The generating function G(·) is C² and strictly positive on an open neighbourhood of the simplex.","type":"model","stated":"explicit","quote":"A portfolio π is said to be functionally generated if there exists a C2, strictly positive function G : U"},{"assumption":"Synthetic data are generated as geometric Brownian motion (GBM) price paths with randomly sampled drifts and volatilities over 1000 days.","type":"data","stated":"explicit","quote":"For synthetic data, we generate geometric Brownian motion (GBM) paths for asset prices and normalise them to compute market weights."},{"assumption":"Real‑world data are daily adjusted closing prices fetched from Yahoo Finance for selected tickers over the past five years.","type":"data","stated":"explicit","quote":"For real data, we fetch daily adjusted closing prices for the selected tickers (e.g., AAPL, MSFT, GOOG, AMZN, META) over the past y = 5 years via Yahoo Finance, ending on Friday, 11 April 2025."},{"assumption":"Training maximises logarithmic portfolio returns relative to the market over a 200‑day window.","type":"execution","stated":"explicit","quote":"The ICNN is trained via back-propagation to maximise logarithmic portfolio returns relative to the market over a window of 200 trading days."}]},"datasets":{"status":"available","items":[{"name":"Synthetic GBM price paths","provider":null,"kind":"synthetic","access":"unknown","period":"1000 days","universe":null,"quote":"For synthetic data, we generate geometric Brownian motion (GBM) paths for asset prices and normalise them to compute market weights."},{"name":"Yahoo Finance daily adjusted closing prices","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"past 5 years ending 11 April 2025","universe":"AAPL, MSFT, GOOG, AMZN, META","quote":"For real data, we fetch daily adjusted closing prices for the selected tickers (e.g., AAPL, MSFT, GOOG, AMZN, META) over the past y = 5 years via Yahoo Finance, ending on Friday, 11 April 2025.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"For real data, we fetch historical prices from Yahoo Finance.","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":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Neural FGP achieves an average logarithmic relative return of 0.078694 on synthetic data, outperforming equally‑weighted, market, and diversity‑weighted benchmarks.","kind":"performance","quote":"FGP 0.078694 EWP 0.0092019 Market -9.79007e-07 DWP p = 0.3 0.00660325 DWP p = 0.5 0.00478323 DWP p = 0.8 0.0019446"},{"finding":"Across all walk‑forward windows, the Neural FGP consistently outperforms the classical benchmark strategies in both synthetic and real‑world evaluations.","kind":"performance","quote":"In both settings, the Neural FGP consistently outperforms all benchmark strategies across nearly all evaluation periods."},{"finding":"The Neural FGP framework preserves self‑financing, pathwise decomposition, and dependence on observable quantities while allowing flexible generating‑function design.","kind":"theoretical","quote":"In our framework, the generating function G(·) is parameterised by a neural network trained on historical market data. This allows the portfolio to adapt to complex, possibly nonlinear features in the market weight dynamics, without sacrificing the interpretability and robustness of the original FGP formulation."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"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":"2026-11-14T17:34:58Z"},"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/"}