{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T22:26:23Z","timestamp":1774736783291,"version":"3.50.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Financial markets operate as dynamic networks in which institutional cross-holdings shape the diffusion of information and the propagation of risk. Forecasting the evolution of stock information networks is critical for anticipating herding behavior and safeguarding systemic stability, yet remains challenging due to high-dimensional heterogeneity, structural non-stationarity, and the need for economically interpretable predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using a quarterly fund\u2013stock holding panel from 2016 to 2024, we construct time-indexed bipartite fund\u2013stock graphs and project them onto the stock layer. From these graphs, we compute two key network indicators: degree centralization (cen_d), capturing market-wide concentration, and residual density (den), reflecting firm-level anomalies. We then develop a large language model (LLM)\u2013enhanced forecasting framework that transforms numeric time series and textual fund disclosures into promptable sequences, incorporates retrieval-augmented historical context, and performs multi-step forecasting of both cen_d and abnormal den spikes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Extensive experiments show that the proposed LLM-based framework significantly reduces mean absolute error and root mean square error, and improves directional accuracy, compared with ARIMA, Prophet, and Temporal Fusion Transformer benchmarks. Attention-weight analysis further indicates that the model assigns higher importance to historical quarters characterized by sharp fund co-movement or policy shocks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings demonstrate that LLM-driven time-series forecasting can provide early warnings of systemic risk and generate economically interpretable insights for investors and regulators. The results highlight the broader potential of language-informed graph forecasting as a new paradigm for financial market surveillance and policy design.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1722121","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T06:42:28Z","timestamp":1769668948000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Large language model-driven time-series forecasting of financial network indicators"],"prefix":"10.3389","volume":"9","author":[{"given":"Mini Han","family":"Wang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Frontiers Science Computing Center, Zhuhai Institute of Advanced Technology Chinese Academy of Sciences","place":["Zhuhai, Guangdong, China"]}]},{"given":"Ying","family":"Yeung","sequence":"additional","affiliation":[{"name":"School of Economic, Shenzhen Polytechnic University","place":["Shenzhen, Guangdong, China"]}]}],"member":"1965","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1108\/imefm-12-2024-0632","article-title":"Stock market predictive modeling using recurring neural network with long short-term architecture","author":"Afzal","year":"2025","journal-title":"Int. J. Islam. Middle East. Finance Manag."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"pgaf089","DOI":"10.1093\/pnasnexus\/pgaf089","article-title":"Measuring gender and racial biases in large language models: intersectional evidence from automated resume evaluation","volume":"4","author":"An","year":"2025","journal-title":"PNAS Nexus"},{"key":"ref3","article-title":"Knowledge graph reasoning over entities and numerical values","author":"Bai","year":"2023","journal-title":"arXiv"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"102616","DOI":"10.1016\/j.inffus.2024.102616","article-title":"Data-driven stock forecasting models based on neural networks: a review","volume":"113","author":"Bao","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1287\/mnsc.2022.02787","article-title":"Can artificial intelligence improve gender equality? Evidence from a natural experiment","volume":"72","author":"Bao","year":"2024","journal-title":"Manag. Sci."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"767","DOI":"10.3390\/forecast4040042","article-title":"Big data and predictive analytics for business intelligence: a bibliographic study (2000\u20132021)","volume":"4","author":"Chen","year":"2022","journal-title":"Forecasting"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s10791-025-09573-7","article-title":"Leveraging large language model as news sentiment predictor in stock markets: a knowledge-enhanced strategy","volume":"28","author":"Chen","year":"2025","journal-title":"Discov. Comput."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1038\/s41562-024-02077-2","article-title":"How human\u2013AI feedback loops alter human perceptual, emotional and social judgements","volume":"9","author":"Glickman","year":"2025","journal-title":"Nat. Hum. Behav."},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/CiFer64978.2025.10975739","article-title":"Leveraging large language models and retrieval-augmented generation for enhanced multi-asset portfolio construction","author":"Hajaghaie","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"121824","DOI":"10.1016\/j.ins.2024.121824","article-title":"Stock complex networks based on the GA-LightGBM model: the prediction of firm performance","volume":"700","author":"Huang","year":"2025","journal-title":"Inf. Sci."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2348540","DOI":"10.1080\/23322039.2024.2348540","article-title":"The role of centralization index in identifying momentum stage of stocks: empirical evidence from investor networks","volume":"12","author":"Liu","year":"2024","journal-title":"Cogent Econ. Financ."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14984969","article-title":"Multimodal data-driven factor models for stock market forecasting","volume":"4","author":"Liu","year":"2025","journal-title":"J. Comput. Technol. Softw."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1108\/qrfm-04-2024-0087","article-title":"Investor sentiment and its implication on global financial markets: a systematic review of literature","author":"Maurya","year":"2025","journal-title":"Qual. Res. Financ. Mark."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"417","DOI":"10.3390\/jrfm18080417","article-title":"DASF-net: a multimodal framework for stock price forecasting with diffusion-based graph learning and optimized sentiment fusion","volume":"18","author":"Nguyen","year":"2025","journal-title":"J. Risk Financ. Manag."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"125299","DOI":"10.1016\/j.eswa.2024.125299","article-title":"An advisor neural network framework using LSTM-based informative stock analysis","volume":"259","author":"Ricchiuti","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-031-88024-7_2","article-title":"Time series analysis from classical methods to transformer-based approaches: a review","volume":"51","author":"Thundiyil","year":"2025","journal-title":"Signal Process. Med. Biol."},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.2174\/97988988122871250101","volume-title":"AI-powered innovations in ophthalmic diagnosis and treatment","author":"Wang","year":""},{"key":"ref18","doi-asserted-by":"publisher","first-page":"6879","DOI":"10.3390\/s25226879","article-title":"Explainable artificial intelligence framework for predicting treatment outcomes in age-related macular degeneration","volume":"25","author":"Wang","year":"","journal-title":"Sensors"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1174","DOI":"10.3390\/bioengineering12111174","article-title":"An explainable AI framework for corneal imaging interpretation and refractive surgery decision support","volume":"12","author":"Wang","year":"","journal-title":"Bioengineering"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2697","DOI":"10.3390\/electronics12122697","article-title":"An explainable artificial intelligence-based robustness optimization approach for age-related macular degeneration detection based on medical IOT systems","volume":"12","author":"Wang","year":"","journal-title":"Electronics"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1527010","DOI":"10.3389\/frai.2025.1527010","article-title":"Applied machine learning in intelligent systems: knowledge graph-enhanced ophthalmic contrastive learning with \u201cclinical profile\u201d prompts","volume":"8","author":"Wang","year":"","journal-title":"Front. Artif. Intell."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"15","DOI":"10.12691\/jfa-10-1-3","article-title":"Herfindahl index methods and special analysis for regional competitiveness inequality evaluation","volume":"10","author":"Wang","year":"2022","journal-title":"J. Financ."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1517918","DOI":"10.3389\/frai.2025.1517918","article-title":"Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions","volume":"8","author":"Wang","year":"","journal-title":"Front. Artif. Intell."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/4754025","article-title":"The effect of online investor sentiment on stock movements: an LSTM approach","volume":"2020","author":"Wang","year":"2020","journal-title":"Complexity"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"012025","DOI":"10.1088\/1742-6596\/2650\/1\/012025","article-title":"Can explainable artificial intelligence optimize the data quality of machine learning model? Taking meibomian gland dysfunction detections as a case study","volume":"2650","author":"Wang","year":"","journal-title":"J. Phys. Conf. Ser."},{"key":"ref26","article-title":"Retrieval-augmented large language models for financial time series forecasting","author":"Xiao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Sentiment analysis of stock market investors and its correlation with stock price using maximum entropy","author":"Xue","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1111\/ecpo.12348","article-title":"Investor network density and stock crash risk","volume":"37","author":"Zhai","year":"2025","journal-title":"Econ. Polit."},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1145\/3717867.3717897","article-title":"Decentralization funded by centralization: understanding crypto joint-investment network","author":"Zhang","year":"2025"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1145\/3747912.3747920","volume-title":"Research on personalized financial product recommendation by integrating large language models and graph neural networks","author":"Zhao","year":"2025"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1722121\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:16:16Z","timestamp":1771924576000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1722121\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":30,"alternative-id":["10.3389\/frai.2026.1722121"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1722121","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"article-number":"1722121"}}