KIT | KIT-Bibliothek | Impressum | Datenschutz

Towards Extracting Causal Graph Structures from Trade Data and Smart Financial Portfolio Risk Management

Ravivanpong, Ployplearn 1; Riedel, Till ORCID iD icon 1; Stock, Pascal
1 Institut für Telematik (TM), Karlsruher Institut für Technologie (KIT)


Risk managers of asset management companies monitor portfolio risk metrics such as the Value at Risk in order to analyze and to communicate the risks timely to portfolio managers, and to ensure regulatory compliance. They must investigate the possible causes if a portfolio risk significantly increases or breaches a regulatory limit. However, monitoring can quickly become overwhelming, time and labor-intensive as each risk manager has to deal with over a hundred portfolios, numerous daily market data, and hundreds of risk factors of the supervised portfolios and of their securities. Particularly, understanding the interrelations between incidents in different portfolios beyond high level indicators is important. However, analyzing these interrelations manually is one of the most difficult tasks. In this paper, we describe and demonstrate how automatically generating causal graphs can address the capacity problem of practitioners in risk management, who are facing more and more capital markets based risk data daily on the portfolio level alone. Based on a proof of concept implementation, we compare a pairwise causal-inference-based approach with a clustering-based construction approach. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000147758
Veröffentlicht am 08.06.2022
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Telematik (TM)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator ISSN: 1613-0073
KITopen-ID: 1000147758
Erschienen in EDBT/ICDT-WS 2022: Proceedings of the Workshops of the EDBT/ICDT 2022 Joint Conference ; Edinburgh, UK, March 29, 2022. Ed.: M. Ramanath
Veranstaltung EDBT/ICDT Joint Conference (2022), Online, 29.03.2022 – 01.04.2022
Serie CEUR Workshop Proceedings ; 3135
Schlagwörter risk management, causal inference, agglomerative hierarchical clustering, network visualization
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page