{"paper_id":"2509.24254","title":"Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns","authors":["Yuntao Wu","Ege Mert Akin","Charles Martineau","Vincent Grégoire","Andreas Veneris"],"paper_date":"2025-09-29","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2509.24254v2","page_url":"https://thequant.space/flowcharts/extracting-the-structure-of-press-releases-for-predicting-ea/","scores":{"empirical_rigor":8.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes an online learning framework that combines bag‑of‑words, BERT and large language models to predict earnings‑announcement returns from press‑release text and to enhance explainability.","quote":"Our contributions are threefold: (1) Unlike conventional approaches based on static train‑test splits, our framework supports online learning and adapts easily to new data; (2) We integrate the advantages of bag‑of‑words, BERT and large language models to enhance explainability by identifying key tokens and topics driv","summary":"We examine how textual features in earnings press releases predict stock returns on earnings announcement days. Using over 138,000 press releases from 2005 to 2023, we compare traditional bag-of-words and BERT-based embeddings. We find that press release content (soft information) is as informative…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Stock prices fully reflect press‑release content at market open (market efficiency).","type":"market","stated":"explicit","quote":"Stock prices fully reflect the content of press releases at market open."},{"assumption":"Trades can be entered at the ask (or bid) price at 9:45 a.m. and exited at the closing price without additional slippage.","type":"execution","stated":"explicit","quote":"We enter trades at 9:45 a.m since bid‑ask spreads are wide at the opening of markets [16, 23], and exit at the 4:00 p.m close."},{"assumption":"Stocks with a relative bid‑ask spread exceeding 20 % of the midquote are excluded as illiquid.","type":"execution","stated":"explicit","quote":"We exclude stocks with excessive illiquidity—defined as a relative bid‑ask spread exceeding 20% of the midquote: |Ask −Bid| / Midquote ≥0.2"},{"assumption":"Press releases are published after‑hours (on or after 4:00 p.m. or before 9:30 a.m. ET), representing the relevant information set.","type":"data","stated":"explicit","quote":"We retain press releases published after hours, i.e., on or after 4:00 p.m. or strictly before 9:30 a.m. ET. This comprises 97% of the dataset."},{"assumption":"Earnings surprise is measured as the scaled difference between actual EPS and consensus forecast five days before the announcement.","type":"statistical","stated":"explicit","quote":"We compute earnings surprises (hard information) as"}]},"datasets":{"status":"available","items":[{"name":"Earnings press releases","provider":"SEC Edgar (8‑K filings)","kind":"text-news","access":"public","period":"2005‑2023","universe":"6,543 unique firms","quote":"We retrieve 158,797 earnings press releases for 6,543 unique firms (PERMNOs in CRSP). After"},{"name":"CRSP Daily Stock Files","provider":"CRSP","kind":"market-prices","access":"commercial","period":"2005‑2023","universe":"All U.S. stocks with earnings announcements","quote":"We retrieve daily stock returns and open and closing prices from CRSP Daily Stock Files","known_id":"crsp"},{"name":"NYSE Trade and Quote (TAQ)","provider":"NYSE","kind":"order-book","access":"commercial","period":"2005‑2023","universe":"Stocks with TAQ data aligned to earnings events","quote":"intraday quotes from NYSE Trade and Quote (TAQ)","known_id":"taq"},{"name":"LSEG IBES Academic","provider":"LSEG","kind":"fundamentals","access":"commercial","period":"2005‑2023","universe":"Analyst forecasts for earnings announcements","quote":"We obtain earnings dates and times, analysts’ forecasts, and announced EPS from LSEG IBES Academic.","known_id":"refinitiv"}],"known":[{"id":"crsp","name":"CRSP","provider":"Center for Research in Security Prices","kind":"market-prices","access":"commercial","quote":"We retrieve daily stock returns and open and closing prices from CRSP Daily Stock Files and intraday quotes from NYSE Trade and Quote (TAQ).","mentions":3,"used_in":2},{"id":"taq","name":"NYSE TAQ","provider":"NYSE","kind":"market-prices","access":"commercial","quote":"We retrieve daily stock returns and open and closing prices from CRSP Daily Stock Files and intraday quotes from NYSE Trade and Quote (TAQ).","mentions":3,"used_in":2},{"id":"ibes","name":"I/B/E/S","provider":"LSEG","kind":"fundamentals","access":"commercial","quote":"We obtain earnings dates and times, analysts’ forecasts, and announced EPS from LSEG IBES Academic.","mentions":1,"used_in":1},{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"We obtain earnings dates and times, analysts’ forecasts, and announced EPS from LSEG IBES Academic.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"tick"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"yes","evidence_card":"partial","evidence_card_quoted":true},"conflict_kind":"graded","card_detail":"Trades are entered at the ask (or bid) price and exited at the closing price; Strategy 2 captures transaction costs by buying at ask and selling at bid.","card_quote":"Enter and exit using ask/bid quotes, capturing transaction costs. For instance, a long position buys at ask and sells at bid.","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Press‑release text (soft information) is as informative as earnings surprise (hard information) for predicting announcement‑day returns, raising R² to about 4 %.","kind":"predictive-accuracy","quote":"Across all model specifications, Soft is positive and statistically significant at the 1% , increasing the 𝑅2 up to 4.4%."},{"finding":"FinBERT provides the largest increase in R² among text models and yields the highest SHAP importance values.","kind":"performance","quote":"The soft model estimated through FinBERT corresponds to the largest increase in 𝑅2 relative to the univariate analysis in Column (1)."},{"finding":"A long‑short trading strategy based on agreement between surprise and SoftMean generates no abnormal profit; estimated alphas are small and negative.","kind":"negative","quote":"... for strategy 2, the corresponding values are 𝛼= −0.0055 and 𝛼= −0.0051, both significant at the 1% level."},{"finding":"When earnings surprise and press‑release content are available in advance (e.g., via hacking), investors can correctly identify 56 % of the top‑10 performing stocks.","kind":"performance","quote":"if earnings surprises and press release content are available in advance, investors can on‑average correctly predict 56% of the top 10 performing stocks using the agreement between hard and soft information."},{"finding":"The framework supports real‑time return prediction through online learning and improves interpretability by identifying key tokens and topics.","kind":"theoretical","quote":"Our framework supports real‑time return prediction through the integration of online learning, provides interpretability and reveals the nuanced role of language in price formation."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":34,"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":1,"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":"2026-11-14T17:26:15Z"},"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/"}