Default Prediction Using Network Based Features

Lorena Poenaru-Olaru*, Judith Redi, Artur Hovanesyan, Huijuan Wang

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

44 Downloads (Pure)


Small and medium enterprises (SME) are crucial for economy and have a higher exposure rate to default than large corporates. In this work, we address the problem of predicting the default of an SME. Default prediction models typically only consider the previous financial situation of each analysed company. Thus, they do not take into account the interactions between companies, which could be insightful as SMEs live in a supply chain ecosystem in which they constantly do business with each other. Thereby, we present a novel method to improve traditional default prediction models by incorporating information about the insolvency situation of customers and suppliers of a given SME, using a graph-based representation of SME supply chains. We analyze its performance and illustrate how this proposed solution outperforms the traditional default prediction approaches.

Original languageEnglish
Title of host publicationComplex Networks and Their Applications X
Subtitle of host publicationProceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1
EditorsRosa Maria Benito, Chantal Cherifi, Hocine Cherifi, Esteban Moro, Luis M. Rocha, Marta Sales-Pardo
Place of PublicationCham
Number of pages12
ISBN (Electronic)978-3-030-93409-5
ISBN (Print)978-3-030-93411-8
Publication statusPublished - 2022
Event10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021 - Hybrid at Madrid, Spain
Duration: 30 Nov 20212 Dec 2021
Conference number: 10th

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503


Conference10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021
CityHybrid at Madrid

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • Default prediction
  • Network centrality
  • Network features
  • Network-based models
  • Transactional network


Dive into the research topics of 'Default Prediction Using Network Based Features'. Together they form a unique fingerprint.

Cite this