{"paper_id":"2402.08233","title":"End-to-End Policy Learning of a Statistical Arbitrage Autoencoder Architecture","authors":["Fabian Krause","Jan-Peter Calliess"],"paper_date":"2024-02-13","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2402.08233v1","page_url":"https://thequant.space/flowcharts/end-to-end-policy-learning-of-a-statistical-arbitrage-autoen/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes embedding an Autoencoder into a neural network that directly outputs portfolio allocations and is trained end‑to‑end on risk‑adjusted returns.","quote":"We propose embedding an Autoencoder in a neural network representing a trading policy, trained end-to-end with a loss function that optimises both portfolio return representation and risk‑adjusted returns.","summary":"In Statistical Arbitrage (StatArb), classical mean reversion trading strategies typically hinge on asset-pricing or PCA based models to identify the mean of a synthetic asset. Once such a (linear) model is identified, a separate mean reversion strategy is then devised to generate a trading signal.…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Asset pricing models rest on the assumption of no arbitrage.","type":"model","stated":"explicit","quote":"Asset pricing models rest on the assumption of no arbitrage - the premise that all excess returns are attributable to risk factors."},{"assumption":"Weights computed at time t can be used to take positions at the beginning of time t+1.","type":"execution","stated":"explicit","quote":"We assume we can take positions using this weight at the beginning of time t + 1 and capture the return from the beginning to the end of t+1."},{"assumption":"Target constant leverage of 1 for the portfolio.","type":"execution","stated":"explicit","quote":"The simplest combination, and the one we use throughout to highlight and compare the modelling aspects of a statistical arbitrage trading pipeline, is to target constant leverage in the portfolio, i.e. wi,t = φi(ǫi,t−τ:t) / ||φi(ǫi,t−τ:t)||1."},{"assumption":"The considered universe of stocks is liquid enough for daily turnover.","type":"market","stated":"explicit","quote":"This assumption is not unrealistic given the liquidity of the considered universe of stocks and the state of electronic markets."},{"assumption":"Universe filtered to exclude low‑price, small‑cap, low‑volume stocks.","type":"data","stated":"explicit","quote":"We restrict our universe by removing any stocks with a close price lower than $5, a 20‑day median rolling market capitalisation of below $1bn, or a 20‑day"}]},"datasets":{"status":"available","items":[{"name":"CRSP stock data","provider":"CRSP","kind":"market-prices","access":"public","period":"January 2000 to December 2022","universe":"US traded companies, primary listing","quote":"stock data was used in the experiments from January 2000 to December 2022.","known_id":"crsp"},{"name":"Fama French factor returns","provider":"Fama French","kind":"benchmark","access":"public","period":"January 2000 to December 2022","universe":null,"quote":"For our benchmark analysis, we use Fama French factor returns for the same time period."}],"known":[],"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":"Our end‑to‑end Autoencoder architecture of learning the entire pipeline in StatArb modelling shows promising results on a pre‑cost basis.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"Our end‑to‑end Autoencoder architecture of learning the entire pipeline in StatArb modelling shows promising results on a pre‑cost basis.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Basic Autoencoder models achieve competitive returns but do not surpass PCA in Sharpe ratio.","kind":"performance","quote":"while the Autoencoder models do not surpass PCA in terms of Sharpe ratio, the regression‑based models deliver competitive, and in some cases superior, returns when compared to the best‑performing PCA models"},{"finding":"The optimal number of latent factors for the policy aligns with literature recommendations of 10‑15.","kind":"theoretical","quote":"the number of latent factors in the best‑performing policy models aligns with the literature’s recommended range of 10 to 15"},{"finding":"The end‑to‑end policy learning approach simplifies strategy development and yields superior gross returns over competitors.","kind":"performance","quote":"Our findings demonstrate that this innovative end‑to‑end policy learning approach not only simplifies the strategy development process, but also yields superior gross returns over its competitors"},{"finding":"Basic Autoencoder implementations can rival established benchmark models like PCA and Fama French in a StatArb context.","kind":"performance","quote":"even basic Autoencoder implementations can rival the performance of established benchmark models like PCA and Fama French in a StatArb context"}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"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":"2026-11-14T18:14:53Z"},"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/"}