{"paper_id":"2410.10614","title":"Modeling News Interactions and Influence for Financial Market Prediction","authors":["Mengyu Wang","Shay B. Cohen","Tiejun Ma"],"paper_date":"2024-10-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.10614v1","page_url":"https://thequant.space/flowcharts/modeling-news-interactions-and-influence-for-financial-marke/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes FININ, a multi‑modal model that quantifies the market impact of individual news items by considering news‑news interactions and links between news and prices.","quote":"We propose FININ, a multi-modal model that quantifies the market impact of individual news items by considering the interactions among news and the links between news and prices.","summary":"The diffusion of financial news into market prices is a complex process, making it challenging to evaluate the connections between news events and market movements. This paper introduces FININ (Financial Interconnected News Influence Network), a novel market prediction model that captures not only…","strategy":"FININ"},"assumptions":{"status":"available","items":[{"assumption":"The target variable is a binary daily market trend indicating price increase (1) or no change/decrease (0).","type":"model","stated":"explicit","quote":"The target variable yd represents the daily market trend, defined as a binary value where 1 signifies a price increase and 0 indicates no change or a decrease between day d and day d + 1."},{"assumption":"Market prediction is performed on a daily basis using data from the prior t days.","type":"data","stated":"explicit","quote":"Our objective is to effectively use the information from the prior t days up to day d, including both market data (M d−t+1, ..., M d−1, M d) and news data (Rd−t+1, ..., Rd−1, Rd), to predict yd."},{"assumption":"News sentiment scores are used as numerical representations of news market sentiment.","type":"data","stated":"explicit","quote":"representing the news market sentiment scores."},{"assumption":"The efficient market hypothesis and information diffusion theory are considered as underlying market theories.","type":"market","stated":"explicit","quote":"It also requires considering established market theories (see §2), such as the efficient market hypothesis and information diffusion theory."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 dataset","provider":null,"kind":"market-prices","access":"commercial","period":"2003 to 2018","universe":"S&P 500 constituents","quote":"... prices from 2003 to 2018 as market numerical data m(n)d."},{"name":"NASDAQ 100 dataset","provider":null,"kind":"market-prices","access":"commercial","period":"2003 to 2018","universe":"NASDAQ 100 constituents","quote":"... NASDAQ 100 prices from 2003 to 2018 as market numerical data m(n)d."},{"name":"Thomson Reuters News Analytics (TRNA) dataset","provider":"Thomson Reuters","kind":"text-news","access":"commercial","period":null,"universe":"over 2.7 million news items","quote":"We use the Thomson Reuters News Analytics (TRNA) dataset, comprising over 2.7 million news items.","known_id":"refinitiv"}],"known":[],"sample":{"start":null,"end":null,"market":"S&P 500 stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"FININ outperforms state‑of‑the‑art market prediction models, improving daily Sharpe ratio by 0.429 for S&P 500 and 0.341 for NASDAQ 100.","kind":"performance","quote":"FININ’s effectiveness, outperforming advanced market prediction models with an improvement of 0.429 and 0.341 in the daily Sharpe ratio for the two markets respectively."},{"finding":"The model reveals a delayed market pricing of news, indicating market inefficiency in incorporating news information.","kind":"theoretical","quote":"FININ highlights a delay in the market pricing of news, indicating market inefficiency in incorporating news information."},{"finding":"Results corroborate the long memory effect of news, showing sustained impact across multiple prediction horizons.","kind":"theoretical","quote":"We corroborate the long memory effect of news (Lillo et al., 2015; Ho et al., 2013)."},{"finding":"Limitations of financial news sentiment analysis are identified, and FININ demonstrates a better ability to extract predictive power beyond sentiment alone.","kind":"theoretical","quote":"We identify the limitations of financial news sentiment analysis and describe how FININ overcomes these limitations."}],"reported_performance":{"strategy":"FININ","sharpe":1.772,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2611.03985","title":"Thinking Fast, Trading Late: System One Decision Models vs the Market","paper_date":"2026-11-02","authors":["Amir Dehkordi","Alireza Kargarzadeh","Nariman Khaledian","Navid Parvini","Sid Ghatak","Arman Khaledian"],"empirical_rigor":9,"page_url":"https://thequant.space/flowcharts/thinking-fast-trading-late-system-one-decision-models-vs-the-market/"},"question":"Does news get incorporated into market prices immediately or with a delay?","this_paper_finding":"The model reveals a delayed market pricing of news, indicating market inefficiency in incorporating news information.","other_paper_finding":"Commercial models predict the overnight gap but not the post‑open move, indicating the market prices the news before traders can act.","other_paper_quote":"The commercial models' readings line up with the overnight move to the open (information coefficient 0.074 to 0.077) but not with the move after it, so the news is priced by the time a trader can act on it at the open.","note":"Finding A shows delayed pricing (market inefficiency); Finding B shows immediate pricing (overnight gap predicted, post‑open not), so they contradict each other.","confidence":0.574}],"qualifies":[],"compared_with":23,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":1,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2503.21422","title":"From Deep Learning to LLMs: A survey of AI in Quantitative Investment","paper_date":"2025-03-27","authors":["Bokai Cao","Saizhuo Wang","Xinyi Lin","Xiaojun Wu","Haohan Zhang","Lionel M. Ni"],"empirical_rigor":1.5,"page_url":"https://thequant.space/flowcharts/from-deep-learning-to-llms-a-survey-of-ai-in-quantitative-i/"},"how":"extends","quote":null},{"paper":{"paper_id":"2510.15691","title":"Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction","paper_date":"2025-10-17","authors":["Tian Guo","Emmanuel Hauptmann"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/exploring-the-synergy-of-quantitative-factors-and-newsflow-r/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T17:58:57Z"},"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/"}