[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81531-en":3,"doc-seo-81531-105":29,"detail-sidebar-cat-0-en-105":82},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},81531,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782698725881665579",8,"Research & Report","Interpretable Role-Based Clustering in Multi-Layer Financial Networks","Understanding the functional roles of financial institutions within interconnected markets is essential for effective supervision, systemic risk assessment, and resolution planning. The document proposes an interpretable role-based clustering framework for multi-layer financial networks, aimed at identifying institutions’ functional positions across market segments. It uses a clustering pipeline based on proximity, evaluation criteria, and algorithm selection, with explainable node embeddings from egonet features capturing direct and indirect trading links within and across layers. Transaction data from the ECB’s MMSR reveals heterogeneous roles such as intermediaries, cross-segment connectors, and peripheral lenders or borrowers, demonstrating practical value in complex market structures.","arXiv :2507 .00600v2 [ cs . SI] 10 Jul 2026  \nInterpretable Role-Based Clustering in Multi-Layer Financial Networks Christian Franssen 1,* , Thao Le 1 , Iman van Lelyveld 1,2 , Bernd Heidergott 1  \n1 VU Amsterdam  \n2 De Nederlandsche Bank  \n* Corresponding author  \nAbstract  \nUnderstanding the functional roles of financial institutions within interconnected markets is critical for effective supervision, systemic risk assessment, and resolution planning. We propose an interpretable rolebased clustering approach for multi-layer financial networks, designed to identify the functional positions of institutions across different market segments. Our method follows a general clustering framework defined by proximity measures, cluster evaluation criteria, and algorithm selection. We construct explainable node embeddings based on egonet features that capture both direct and indirect trading relationships within and across market layers. Using transaction-level data from the ECB’s Money Market Statistical Reporting (MMSR), we demonstrate how the approach uncovers heterogeneous institutional roles such as market intermediaries, cross-segment connectors, and peripheral lenders or borrowers. The results highlight the flexibility and practical value of role-based clustering in analyzing financial networks and understanding institutional behavior in complex market structures.  \nKeywords: financial networks; multi-layer networks; role-based clustering; node embeddings; interbank markets; systemic risk  \n1 Introduction  \nUnderstanding the structure of financial networks is essential for central banks seeking to monitor market functioning, assess systemic risk, and ensure the effective transmission of monetary policy. In these networks, financial institutions are modeled as nodes and transactions as directed edges, enabling detailed analysis of liquidity flows, intermediation chains, and cross-market dynamics [1, 2] . Over the past two decades, financial network analysis has become a foundational tool in macroprudential supervision, with studies showing how the architecture of interbank markets influences contagion (e.g., see Allen and Gale [3], Battiston et al. [4], Staum [5], Acemoglu et al. [6]), market segmentation [7, 8], and the effectiveness of central bank interventions [8, 9] . An important contribution to the study of money market networks is provided by Craig and von Peter [10], who demonstrate that the German money market exhibits a core-periphery structure, with central institutions acting as intermediaries for those on the periphery. Similar structural patterns have been observed in other interbank markets, including those of the Netherlands and Brazil [11, 12] . Carre˜no and Cifuentes [13] also postulate a core-periphery model on Chilean inter-bank exposures and find a dynamic main core, occasionally a secondary core, and several functionally distinct (net lending and borrowing) peripheries whose membership shifts over time and can differ across instruments. Moreover, Kojaku et al. [14] model the Italian eMID while  \nallowing for multiple core–periphery structures and shows that the Italian eMID network comprises several of these.  \nUnderstanding the roles that financial institutions occupy within such networks is crucial for assessing market functioning and regulatory oversight. For example, Kojaku et al. [14] find that the e-MID overnight market switched from multiple core–periphery pairs to a bipartite, broker-driven structure during the 2007-2009 financial crisis, re-assigning formerly peripheral banks into bridging positions. Such functional transitions can serve as indicators of market stress. Moreover, role identification also shapes resolution policy: Jackson and Pernoud [15] find that, counter-intuitively, rescuing peripheral banks can be significantly more cost-effective than bailing out core institutions. Relatedly, connectivity and substitutability are important considerations in determining whether a bank is classifi","cbCaiePo3t349onh","https://ap.wps.com/l/cbCaiePo3t349onh","pdf",2794910,1,23,"English","en",105,"# Introduction\n## Financial network analysis and supervision\n## Functional roles and crisis-driven transitions\n## Motivation: fragmented funding markets across segments\n## Paper contribution and approach overview","[{\"question\":\"What data source is used to demonstrate the approach, and what kinds of roles are uncovered?\",\"answer\":\"The document uses transaction-level data from the ECB’s Money Market Statistical Reporting (MMSR). The results uncover heterogeneous roles including market intermediaries, cross-segment connectors, and peripheral lenders or borrowers.\"}]",1784174086,58,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":27},"interpretable-role-based-clustering-in-multi-layer-financial-networks","",{"@graph":35,"@context":76},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/interpretable-role-based-clustering-in-multi-layer-financial-networks/81531/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"What data source is used to demonstrate the approach, and what kinds of roles are uncovered?","Question",{"text":74,"@type":75},"The document uses transaction-level data from the ECB’s Money Market Statistical Reporting (MMSR). The results uncover heterogeneous roles including market intermediaries, cross-segment connectors, and peripheral lenders or borrowers.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,106,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":45,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general"]