{"paper_id":"2510.20699","title":"Fusing Narrative Semantics for Financial Volatility Forecasting","authors":["Yaxuan Kong","Yoontae Hwang","Marcus Kaiser","Chris Vryonides","Roel Oomen","Stefan Zohren"],"paper_date":"2025-10-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.20699v1","page_url":"https://thequant.space/flowcharts/fusing-narrative-semantics-for-financial-volatility-forecast/","scores":{"empirical_rigor":7,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes M2VN, a Multi-Modal Volatility Network that aligns and fuses news embeddings with time series data for volatility forecasting.","quote":"We propose M2VN: Multi-Modal Volatility Network, a novel framework to align and fuse news embeddings with time series data for the task of financial volatility forecasting.","summary":"We introduce M2VN: Multi-Modal Volatility Network, a novel deep learning-based framework for financial volatility forecasting that unifies time series features with unstructured news data. M2VN leverages the representational power of deep neural networks to address two key challenges in this…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"News articles are temporally aligned on a daily basis.","type":"data","stated":"implied","quote":"All news articles are temporally aligned on a daily basis in a structured format."},{"assumption":"The dataset consists of daily end‑of‑day OHLCV and full‑text news for seven large‑cap U.S. equities.","type":"market","stated":"implied","quote":"... extract both end-of-day price information (open, high, low, close and volume) and the full text of associated news articles from FNSPID [14]."}]},"datasets":{"status":"available","items":[{"name":"Seven large‑cap U.S. equities panel","provider":"FNSPID","kind":"market-prices","access":"public","period":"2013-01-01 to 2023-12-31","universe":"KO, CMCSA, COP, GILD, MRK, NKE, ORCL","quote":"... extract both end-of-day price information (open, high, low, close and volume) and the full text of associated news articles from FNSPID [14].","known_id":"fnspid"},{"name":"M2VN pre‑processed dataset and code","provider":"GitHub repository","kind":"benchmark","access":"public","period":null,"universe":null,"quote":"The pre‑processed dataset, raw news article data, and implementation code are publicly accessible at https://github.com/Yoontae6719/M2VN-Multi-Modal-Learning-Network-for-Volatility-Forecasting"}],"known":[{"id":"fnspid","name":"FNSPID","provider":"Dong et al.","kind":"text-news","access":"public","quote":"For each ticker, we extract both end-of-day price information (open, high, low, close and volume) and the full text of associated news articles from FNSPID [14].","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"M2VN consistently outperforms existing baselines on volatility forecasting.","kind":"performance","quote":"Extensive experiments demonstrate that M2VN consistently outperforms existing baselines, underscoring its practical value for risk management and financial decision‑making."},{"finding":"Ablating the cross‑modal alignment loss reduces mean QLike by 11.7% and MAPE by 3.6%.","kind":"predictive-accuracy","quote":"ablation of our backbone that omits the cross-modal alignment loss Lalign, mean QLike and MAPE fall by 11.7 % and 3.6 %, respectively."},{"finding":"Including trading volume improves forecasting accuracy, reducing average MAPE by 2.86% and QLike by 5.64% across all stocks.","kind":"predictive-accuracy","quote":"On average, incorporating volume reduces MAPE by 2.86±3.06% and QLike by 5.64±2.40% across all stocks."},{"finding":"News embeddings improve performance; e.g., for Coca‑Cola, QLike drops from 0.0641 to 0.0589 and MAPE from 0.2904 to 0.2771.","kind":"predictive-accuracy","quote":"Coca-Cola (KO), the QLike decreased from 0.0641 to 0.0589 and MAPE from 0.2904 to 0.2771 when news was incorporated."},{"finding":"Visual comparison shows M2VN tracks ground‑truth volatility fluctuations and sharp peaks better than HAR‑X and TimeXer baselines.","kind":"performance","quote":"The M2VN demonstrates a superior ability to track the fluctuations and sharp peaks of the ground truth data compared to the other models."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":53,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"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/Yoontae6719/M2VN-Multi-Modal-Learning-Network-for-Volatility-Forecasting","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":"2026-11-14T17:23:54Z"},"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/"}