{"paper_id":"2312.16448","title":"Randomized Signature Methods in Optimal Portfolio Selection","authors":["Erdinc Akyildirim","Matteo Gambara","Josef Teichmann","Syang Zhou"],"paper_date":"2023-12-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2312.16448v1","page_url":"https://thequant.space/flowcharts/randomized-signature-methods-in-optimal-portfolio-selection/","scores":{"empirical_rigor":7,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using Randomized Signature Methods as a non‑linear, non‑parametric drift estimator for portfolio selection.","quote":"We present convincing empirical results on the application of Randomized Signature Methods for non-linear, non-parametric drift estimation for a multi-variate financial market.","summary":"We present convincing empirical results on the application of Randomized Signature Methods for non-linear, non-parametric drift estimation for a multi-variate financial market. Even though drift estimation is notoriously ill defined due to small signal to noise ratio, one can still try to learn…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Preferences of the investor are known.","type":"model","stated":"explicit","quote":"In our context, we assume that the preferences are known and the stochastic process S is determined by an Itˆo semi-martingale with continuous trajectories"},{"assumption":"Asset price dynamics follow an Itô semi‑martingale with continuous trajectories.","type":"market","stated":"explicit","quote":"we let [−Tobs, 0] to be the observation period and (s 7−→Xs)s∈[−Tobs,0] to be the observed data trajectory."},{"assumption":"Drift and volatility functions are unknown and path‑dependent.","type":"model","stated":"explicit","quote":"once all factor processes are considered, the quadratic covariation is calculated as follows..."},{"assumption":"A mild martingale assumption on the stochastic integral for drift estimation.","type":"statistical","stated":"explicit","quote":"Next we consider the task of drift estimation (under a mild martingale assumption on the stochastic integral):"},{"assumption":"No short‑selling and maximum weight per asset limited to 20%.","type":"execution","stated":"explicit","quote":"we impose holding constraints on the weights by not allowing short selling and additionally limiting the maximum allowed weight per single asset at 20% of the total assets."},{"assumption":"Transaction costs are ignored for simulated‑data experiments.","type":"execution","stated":"explicit","quote":"For the sake of simplicity, we do not consider transaction costs for our experiments using simulated data"}]},"datasets":{"status":"available","items":[{"name":"S&P 500 data","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":"S&P 500 constituents","quote":"In our experiments, we choose rm ∈{0, 0.05, 0.1}, rv ∈{0.01, 0.03, 0.05, 0.3, 1.0} and rd ∈{50, 60, 70, 100}, respectively."},{"name":"Synthetic simulations","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"In this section we present the empirical results from our algorithm with two different portfolio construction methodologies using both real and simulated prices"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":null,"detail":"Four cost levels are examined (0%, 0.3%, 0.6%, 1%) with hyper‑parameter tuning; costs are applied only in real‑world data experiments.","quote":"Figure 9: Performance under four different transaction costs, namely {0%, 0.3%, 0.6%, 1%}.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Four cost levels are examined (0%, 0.3%, 0.6%, 1%) with hyper‑parameter tuning; costs are applied only in real‑world data experiments.","card_quote":"Figure 9: Performance under four different transaction costs, namely {0%, 0.3%, 0.6%, 1%}.","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":"The Randomized Signature strategy out‑performed the 1/n benchmark on monthly returns in 67.28% of the months in simulated data.","kind":"performance","quote":"if we consider the 1/n strategy as a possible competitor, from Figure 4 we observe that our methodology over-performed the former 67.28% of the times on monthly returns."},{"finding":"Across the full real‑world period, the proposed portfolio out‑performed all benchmark portfolios for all transaction‑cost levels.","kind":"performance","quote":"Overall, one can see that our strategy outperforms the benchmark portfolio on most of the time segments and trading cost levels."},{"finding":"Even with the worst hyper‑parameter configuration, the method delivered higher annualised return and Sharpe ratio than benchmarks.","kind":"performance","quote":"Even though the results vary significantly over the hyper-parameter space used for our experiments, we show that our portfolio over-performs for both annualized return and annualized Sharpe ratio even in the worst hyper-parameter configuration."},{"finding":"When signal‑to‑noise ratio falls below a lower bound, all predictions break down and the 1/n portfolio becomes best.","kind":"negative","quote":"It also suggests that there is a lower bound for the signal-to-noise ratio under which all predictions break down and the one-over-n portfolio becomes the best-performing portfolio."},{"finding":"The method is robust to transaction costs; performance degrades gracefully as costs increase.","kind":"performance","quote":"seen, for the environment without transaction costs, the best hyper-parameter configurations are in the upper left corner, whereas with increasing transaction costs, the best-performing configurations move more and more to the lower right corner."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":4,"by_independent_authors":4,"how_cited":{"used_as_baseline":0,"uses_method_or_data":2,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2406.10214","title":"Universal randomised signatures for generative time series modelling","paper_date":"2024-06-14","authors":["Francesca Biagini","Lukas Gonon","Niklas Walter"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/universal-randomised-signatures-for-generative-time-series-modelling/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2507.10701","title":"Kernel Learning for Mean-Variance Trading Strategies","paper_date":"2025-07-14","authors":["Owen Futter","Nicola Muca Cirone","Blanka Horvath"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/kernel-learning-for-mean-variance-trading-strategies/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T18:17:16Z"},"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/"}