{"paper_id":"2311.10685","title":"High-Throughput Asset Pricing","authors":["Andrew Y. Chen","Chukwuma Dim"],"paper_date":"2023-11-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2311.10685v3","page_url":"https://thequant.space/flowcharts/high-throughput-asset-pricing/","scores":{"empirical_rigor":6,"math_complexity":5.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a high‑throughput empirical Bayes framework to mine 136,000 long‑short strategies and obtain unbiased out‑of‑sample predictions.","quote":"We apply empirical Bayes (EB) to mine data on 136,000 long-short strategies constructed from accounting ratios, past returns, and ticker symbols. This ``high-throughput asset pricing'' matches the out-of-sample performance of top journals while eliminating look-ahead bias.","summary":"We apply empirical Bayes (EB) to mine data on 136,000 long-short strategies constructed from accounting ratios, past returns, and ticker symbols. This ``high-throughput asset pricing’’ matches the out-of-sample performance of top journals while eliminating look-ahead bias. Naively mining for the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Standard errors of raw long‑short returns are precisely measured.","type":"statistical","stated":"explicit","quote":"We select as our performance measure the t-statistic on the raw long-short return, and assume that standard errors are precisely measured, implying ri|µi, Xi ∼Normal(µi,1) (13)"},{"assumption":"Long sample periods (e.g., 300 months) and standardized performance measures (t‑statistics) satisfy Conditions 1 and 2.","type":"statistical","stated":"explicit","quote":"Conditions 1 and 2 arise naturally when using long samples (e.g. 300 months of returns), standardized performance measures (e.g. t-statistics), and strict statistical hurdles (e.g. 5% critical levels)."},{"assumption":"Latent performance follows a two‑component normal mixture that depends on strategy family.","type":"model","stated":"explicit","quote":"The latent performance is a mixture of two normals that depends on the strategy family Di. µi | (Xi,Di = d) ∼ { Normal(θd,1,σ2d,1) with prob λd; Normal(θd,2,σ2d,2) otherwise } (14)."}]},"datasets":{"status":"available","items":[{"name":"Accounting Ratio Strategies","provider":"Chen, Lopez‑Lira, and Zimmermann (2022)","kind":"fundamentals","access":"public","period":null,"universe":null,"quote":"We examine 60,000 accounting ratio strategies constructed by Chen, Lopez‑Lira, and Zimmermann (2022)."},{"name":"Past Return‑Based Strategies","provider":"Inspired by Yan and Zheng (2017)","kind":"other","access":"public","period":null,"universe":null,"quote":"Inspired by Yan and Zheng (2017) , we construct past-return strategies as follows: Choose 4 quarters out of the past 20 quarters…"},{"name":"Ticker‑Based Strategies","provider":"Inspired by Harvey (2017)","kind":"alternative","access":"public","period":null,"universe":null,"quote":"The past return and ticker strategies are inspired by Yan and Zheng (2017) and Harvey (2017), respectively, but we generate our own strategies in order to ensure that the number of strategies is comparable across data sources."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"n/a","evidence_card_quoted":false},"conflict_kind":"applicability","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The top 1% of EB‑mined strategies earn 5.70% per year with a Sharpe ratio of 1.46, comparable to published strategies (5.88% return, Sharpe 2.03) but without look‑ahead bias.","kind":"performance","quote":"Using empirical Bayes (EB Mining), the top 1% of strategies perform similarly to strategies published in top finance journals. Over the full 1983-2020 sample, the top 1% portfolio earns 5.70% per year, compared to the 5.88% return from published strategies. The Sharpe ratio from EB mining is smaller, at 1.46 vs 2.03 fo"},{"finding":"Naïve data mining by selecting the top 1% based on past Sharpe ratios yields an out‑of‑sample Sharpe of 1.45, essentially the same as EB mining.","kind":"performance","quote":"Simply choosing the top 1% of strategies based on their past Sharpe ratios leads to an out-of-sample Sharpe ratio of 1.45. This is almost exactly the same as the Sharpe ratio from the top 1% using EB mining, consistent with Proposition 1."},{"finding":"Predictability is concentrated in accounting signals, small stocks, and pre‑2004 periods, supporting limited‑attention and mispricing theories.","kind":"statistical","quote":"This high-throughput method shows that returns are concentrated in accounting signals, small stocks, and pre-2004 periods, consistent with mispricing and slow information diffusion theories."},{"finding":"Multiple testing methods popular in finance would miss most out‑of‑sample performers, whereas methods from the statistics literature perform well.","kind":"statistical","quote":"We find that methods popular in finance would lead researchers to miss out on the majority of signals with notable out-of-sample performance. In contrast, methods recommended by the statistics literature perform well."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"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/chenandrewy/high-throughput-ap","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":"2026-11-14T18:19:36Z"},"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/"}