[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126219-en":3,"doc-seo-126219-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126219,549768702563,"Sage","https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083",8,"Research & Report","Forecasting Financial Market Structure using Machine Learning","A machine learning model forecasts market correlation structure by representing market structure as a dynamic asset network. The approach quantifies time-dependent co-movement in asset price returns using link- and node-based financial network features across constituents of major global market indices. Three network filtering methods—Dynamic Asset Graph (DAG), Dynamic Minimal Spanning Tree (DMST), and Dynamic Threshold Networks (DTN)—produce empirical market-structure estimates. Results show high predictive performance, including up to 40% improvement over a time-invariant correlation benchmark, with non pair-wise features crucial for long-term structure forecasting, supporting portfolio selection and risk management.","Forecasting Financial Market Structure from Network Features using Machine Learning  \nDouglas Castilho 1,5 , Thársis T. P. Souza2 , Soong Moon Kang3 , João Gama4 and André C. P. L. F. de Carvalho 1  \n1 Institute of Mathematics and Computer Sciences (ICMC), University of São Paulo (USP), São Carlos, Brazil.  \n2 Department of Computer Science, University College London, Gower Street, London, WC1E 6BT, UK.  \n3 School of Management, University College London, Gower Street, London, WC1E 6BT, UK.  \n4 Institute for Systems and Computer Engineering, Technology and Science, University of Porto (UP), Porto, Portugal.  \n5 Laboratory of Technology and Innovation (LATIN), Federal Institute of South of Minas Gerais (IFSULDEMINAS), Poços de  \nCaldas, Brazil.  \nAbstract  \nWe propose a model that forecasts market correlation structure from link- and node-based financial network features using machine learning. For such, market structure is modeled as a dynamic asset network by quantifying time-dependent co-movement of asset price returns across company constituents of major global market indices. We provide empirical evidence using three different network filtering methods to estimate market structure, namely Dynamic Asset Graph (DAG), Dynamic Minimal Spanning Tree (DMST) and Dynamic Threshold Networks (DTN) . Experimental results show that the proposed model can forecast market structure with high predictive performance with up to 40% improvement over a time-invariant correlation-based benchmark. Non pair-wise correlation features showed to be important compared to traditionally used pair-wise correlation measures for all markets studied, particularly in the long-term forecasting of stock market structure. Evidence is provided for stock constituents of the DAX30, EUROSTOXX50, FTSE100, HANGSENG50, NASDAQ100 and  \n2 Forecasting Financial Market Structure using Machine Learning  \nNIFTY50 market indices. Findings can be useful to improve portfolio selection and risk management methods, which commonly rely on a backward-looking covariance matrix to estimate portfolio risk.  \nKeywords: Financial Networks, Network Link Prediction, Information  \nFiltering Networks, Correlation-Based Networks, Machine Learning, Stock  \nMarkets  \n1 Introduction  \nMulti-asset financial analyses, particularly optimal portfolio selection and portfolio risk management, traditionally rely on the usage of a covariance matrix representative of market structure, which is commonly assumed to be time invariant. Under this assumption, however, non-stationarity [1, 2] and long range memory [3] can lead to misleading conclusions and spoil the ability to explain future market structure dynamics.  \nEmpirical analyses of networks in finance have been used successfully to study market structure dynamics, particularly to explain market interconnectedness from high-dimensional data [4–7] . Under this approach, market structure is modeled as a network whose nodes represent different financial assets and edges represent one or many types of relevant relationships among those assets. There is a vast literature applying financial networks to descriptive analysis of market and portfolio dynamics, including market stability [8], information extraction [9], asset allocation [10, 11] and dependency structure [4, 12–15] . However, there is little research on the application of financial networks in market structure forecasting. Recent research on market structure inference makes use of information filtering networks to produce a robust estimate of the global sparse inverse covariance matrix [16], achieving computationally efficient results. In a later study [17], the authors forecast market structure based on a model that uses a principle of link formation by triadic closure in stock market networks. Spelta [18] proposed a method to predict abrupt market changes, inferring the future dynamics of stock prices by predicting future distances between them, using a tensor decomposition technique. Musm","cbCainYOiSjDZMxY","https://ap.wps.com/l/cbCainYOiSjDZMxY","pdf",3578828,7,1,34,"English","en",105,"# Introduction\n## Market structure as a dynamic network\n## Motivation: limitations of time-invariant covariance\n## Related work in network-based finance\n## Formulation as a link prediction problem","[{\"question\":\"How does the model forecast market correlation structure?\",\"answer\":\"It formulates market structure forecasting as a link prediction task, estimating the probability of adding or removing links in future dynamic networks using node- and link-specific features.\"},{\"question\":\"Which network filtering methods are used to estimate market structure?\",\"answer\":\"The study evaluates Dynamic Asset Graph (DAG), Dynamic Minimal Spanning Tree (DMST), and Dynamic Threshold Networks (DTN) to estimate market structure from financial networks.\"},{\"question\":\"What performance gain is reported compared with a benchmark?\",\"answer\":\"Experimental results indicate up to 40% improvement over a time-invariant correlation-based benchmark for forecasting market structure.\"}]","Forecasting Financial Market Structure using Machine Learning | PDF",1785903870,86,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"forecasting-financial-market-structure-using-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/forecasting-financial-market-structure-using-machine-learning/126219/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"How does the model forecast market correlation structure?","Question",{"text":77,"@type":78},"It formulates market structure forecasting as a link prediction task, estimating the probability of adding or removing links in future dynamic networks using node- and link-specific features.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which network filtering methods are used to estimate market structure?",{"text":82,"@type":78},"The study evaluates Dynamic Asset Graph (DAG), Dynamic Minimal Spanning Tree (DMST), and Dynamic Threshold Networks (DTN) to estimate market structure from financial networks.",{"name":84,"@type":75,"acceptedAnswer":85},"What performance gain is reported compared with a benchmark?",{"text":86,"@type":78},"Experimental results indicate up to 40% improvement over a time-invariant correlation-based benchmark for forecasting market structure.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]