{"paper_id":"2309.16008","title":"Optimal Entry and Exit with Signature in Statistical Arbitrage","authors":["Boming Ning","Prakash Chakraborty","Kiseop Lee"],"paper_date":"2023-09-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.16008v4","page_url":"https://thequant.space/flowcharts/optimal-entry-and-exit-with-signature-in-statistical-arbitra/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a sequential optimal stopping framework solved via a refined signature optimal stopping method to determine optimal entry and exit timings for mean‑reverting spreads.","quote":"Then we leverages a refined signature optimal stopping method to resolve this sequential optimal stopping problem, thereby unveiling the precise entry and exit timings that maximize gains.","summary":"In this paper, we explore an optimal timing strategy for the trading of price spreads exhibiting mean-reverting characteristics. A sequential optimal stopping framework is formulated to analyze the optimal timings for both entering and subsequently liquidating positions, all while considering the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The price or portfolio value follows a mean‑reverting process.","type":"model","stated":"explicit","quote":"Suppose that the investor trades on a spread or portfolio whose value process (Xt)t≥0 follows a mean reverting process."},{"assumption":"A constant transaction cost c>0 is incurred when entering a long position.","type":"execution","stated":"explicit","quote":"If the long position is opened at some time τ0 > 0, then the investor will pay the value Xτ0 plus a constant transaction cost c > 0."},{"assumption":"A constant transaction cost ˆc>0 is incurred when exiting a position.","type":"execution","stated":"explicit","quote":"If the position is closed at time ν0, the investor will receive the value Xν0 and pay a constant transaction cost ˆc > 0."},{"assumption":"The investor discounts cash flows at a constant rate r>0 (and possibly a different rate ˆr for post‑entry).","type":"model","stated":"explicit","quote":"Assuming that r > 0 is the investor’s subjective constant discount rate, the total cost of entering a long position is e−rτ0(Xτ0 + c)."},{"assumption":"The signature method only requires the underlying path to be a continuous (geometric) random rough path.","type":"model","stated":"explicit","quote":"Importantly, this method does not require specific assumptions about the underlying stochastic process other than it being a continuous (geometric) random rough path."},{"assumption":"The pre‑entry and post‑entry discount rates and transaction costs may differ.","type":"model","stated":"explicit","quote":"Note that the pre-entry and post-entry discount rates, ˆr and r, as well as the entry and exit transaction costs ˆc and c, can differ in our analysis."}]},"datasets":{"status":"available","items":[{"name":"Synthetic OU training set","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"In the first phase, we synthesize a dataset consisting of 100 training samples. These samples are used to compute the optimal linear function l∗ that minimizes the loss function."},{"name":"Synthetic OU testing set","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"In the second phase, we generate a supplementary set of 10 testing samples. Utilizing the previously computed optimal linear function l∗, we ascertain the optimal stopping times for these test cases."},{"name":"Four pairs portfolios (WM/RSG, UAL/DAL, V/MA, GS/MS)","provider":null,"kind":"market-prices","access":"unknown","period":"one‑year","universe":"four equity pairs","quote":"Table 3: Performance summary for all 4 pairs portfolios for baseline and the signature optimal trading (SOT)."}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The data was sourced via the Yahoo! Finance API1.","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":"yes","headline_net_of_costs":null,"detail":"Constant entry cost c>0 and constant exit cost ˆc>0 are incorporated into the optimal stopping objectives.","quote":"If the long position is opened at some time τ0 > 0, then the investor will pay the value Xτ0 plus a constant transaction cost c > 0","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Constant entry cost c>0 and constant exit cost ˆc>0 are incorporated into the optimal stopping objectives.","card_quote":"If the long position is opened at some time τ0 > 0, then the investor will pay the value Xτ0 plus a constant transaction cost c > 0","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The signature optimal trading (SOT) strategy yields substantially higher cumulative returns and Sharpe ratios than the baseline across all four pairs.","kind":"performance","quote":"our proposed signature optimal trading strategy substantially outperforms the baseline model in key performance metrics, including higher cumulative returns and a more"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":7,"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":"2026-11-14T18:21:44Z"},"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/"}