{"paper_id":"2510.11616","title":"Attention Factors for Statistical Arbitrage","authors":["Elliot L. Epstein","Rose Wang","Jaewon Choi","Markus Pelger"],"paper_date":"2025-10-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.11616v1","page_url":"https://thequant.space/flowcharts/attention-factors-for-statistical-arbitrage/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an Attention Factor Model that jointly learns tradable arbitrage factors and portfolio allocations in a one‑step framework optimized for trading costs.","quote":"In this paper, we propose the Attention Factor Model, a framework that jointly learns tradable arbitrage factors and arbitrage portfolio allocations in a computationally efficient manner.","summary":"Statistical arbitrage exploits temporal price differences between similar assets. We develop a framework to jointly identify similar assets through factors, identify mispricing and form a trading policy that maximizes risk-adjusted performance after trading costs. Our Attention Factors are…","strategy":"Attention Factors"},"assumptions":{"status":"available","items":[{"assumption":"Asset returns follow a conditional factor model with time‑varying loadings based on lagged information.","type":"model","stated":"explicit","quote":"We assume that asset returns can be modeled by a conditional factor model: 𝑅𝑖,𝑡= 𝛽𝑇𝑖,𝑡−1𝐹𝑡+ 𝜖𝑖,𝑡,"},{"assumption":"Only the 500 most liquid U.S. equities (largest by market cap) are used in the empirical analysis.","type":"data","stated":"explicit","quote":"We consider only the 500 largest stocks based on the previous month market capitalization."}]},"datasets":{"status":"available","items":[{"name":"CRSP daily equity returns","provider":"CRSP","kind":"market-prices","access":"public","period":"January 1990 through December 2021","universe":"500 largest U.S. stocks","quote":"We collect daily equity return data for the securities on CRSP from January 1990 through December 2021.","known_id":"crsp"},{"name":"Firm-specific characteristics","provider":"CRSP/Compustat","kind":"fundamentals","access":"public","period":null,"universe":null,"quote":"... All these variables are constructed either from accounting variables from the CRSP/Compustat database or from past returns from CRSP.","known_id":"crsp"}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"All these vari-ables are constructed either from accounting variables from the CRSP/Compustat database or from past returns from CRSP.","mentions":3,"used_in":2},{"id":"compustat","name":"Compustat","provider":"S&P Global","kind":"fundamentals","access":"commercial","quote":"All these vari-ables are constructed either from accounting variables from the CRSP/Compustat database or from past returns from CRSP.","mentions":1,"used_in":1}],"sample":{"start":"1998","end":"2021","market":"U.S. equities","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"Cost = 0.0005 per unit turnover (5 bps) plus 0.0001 per unit short position (1 bp). Net return = gross return minus this cost.","quote":"... The portfolio net return is then calculated as: 𝑅port𝑡,𝑛𝑒𝑡= 𝑅port𝑡−cost(𝜔𝑡,𝜔𝑡−1).","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Cost = 0.0005 per unit turnover (5 bps) plus 0.0001 per unit short position (1 bp). Net return = gross return minus this cost.","card_quote":"... The portfolio net return is then calculated as: 𝑅port𝑡,𝑛𝑒𝑡= 𝑅port𝑡−cost(𝜔𝑡,𝜔𝑡−1).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The Attention Factor model achieves an out‑of‑sample Sharpe ratio above 4 before costs and a net Sharpe of 2.3 after transaction costs.","kind":"performance","quote":"Our Attention Factor model provides unprecedented performance of 2.3 after trading costs."},{"finding":"Simple PCA factor models suffer from high turnover, yielding a net Sharpe around 1.5 after costs.","kind":"performance","quote":"a simple PCA factor model cannot adjust the factor construction to trading frictions, resulting in a deterioration of the net performance to a Sharpe ratio of around 1.5."},{"finding":"Including weak factors improves performance; using 30 attention factors outperforms using only 8.","kind":"performance","quote":"We observe an out‑of‑sample improvement for including 30 factors. These higher order factors capture weak signals and local dependency patterns."},{"finding":"The model learns economically meaningful factor loadings that cluster firms by industry without using explicit industry labels.","kind":"other","quote":"Firms in similar industries are grouped together, that is, our model learns specific industries. For example, the upper right cluster represents banks and financial ..."}],"reported_performance":{"strategy":"Attention Factors","sharpe":3.97,"sharpe_benchmark":null,"annual_return_pct":16.66,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":30,"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":"2026-11-14T17:24:45Z"},"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/"}