{"paper_id":"2306.16422","title":"Neural networks can detect model-free static arbitrage strategies","authors":["Ariel Neufeld","Julian Sester"],"paper_date":"2023-06-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.16422v2","page_url":"https://thequant.space/flowcharts/neural-networks-can-detect-model-free-static-arbitrage-strat/","scores":{"empirical_rigor":6,"math_complexity":9,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a neural network based method that can detect model‑free static arbitrage opportunities in markets with many securities.","quote":"we demonstrate both theoretically as well as numerically that neural networks can detect model-free static arbitrage opportunities whenever the market admits some.","summary":"In this paper we demonstrate both theoretically as well as numerically that neural networks can detect model-free static arbitrage opportunities whenever the market admits some. Due to the use of neural networks, our method can be applied to financial markets with a high number of traded securities…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The market allows static trading in options.","type":"market","stated":"explicit","quote":"In this section, we study a financial market in which a financial agent can trade statically in various types of options"},{"assumption":"Underlying assets are scaled to 1 and their values at maturity lie in [0,2] per dimension (0%–200% of spot).","type":"model","stated":"explicit","quote":"The spot values of the underlying assets are scaled to 1, therefore the strikes and corresponding prices are included as percentage values w.r.t. the spot value of the underlying asset. We assume S = [0, 2]5, i"},{"assumption":"Option data are taken from the 10 most liquidly traded call options per S&P 500 constituent with a fixed maturity.","type":"data","stated":"explicit","quote":"To create a training set we consider for each of the 500 constituents of the S&P 500 the 10 most liquidly traded"}]},"datasets":{"status":"available","items":[{"name":"S&P 500 call options dataset","provider":"Yahoo Finance","kind":"options","access":"public","period":"maturity T = 19 May 2023 (data downloade","universe":"500 S&P 500 constituents, 10 most liquid call options each","quote":"To create a training set we consider for each of the 500 constituents of the S&P 500 the 10 most liquidly traded","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The data was downloaded on 25 April 2023 via Yahoo Finance.","mentions":1,"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":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The neural network correctly identifies arbitrage on 92.81% of training samples (41 768 / 45 000).","kind":"performance","quote":"After training on the 45 000 samples, the neural network assigns to 41 768 out of 45 000 the correct sign of the price of the strategy learned by the neural network, i.e., in 92.81% of cases on the training set, the neural network can correctly decide whether the market admits arbitrage or not."},{"finding":"On the test set the network achieves 89.20% correct arbitrage identification (4 460 / 5 000).","kind":"performance","quote":"On the test set we have 4460 out of 5000 correct identifications which corresponds to 89.20%."},{"finding":"In the vast majority of 1 000 000 evaluated test cases the net profit of the suggested strategy is positive.","kind":"theoretical","quote":"The results verify that on the test set the net profit is in the vast majority of the 1 000 000 evaluated cases positive"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":8,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/juliansester/Deep-Arbitrage","note":null},"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":"2026-11-14T18:25:41Z"},"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/"}