Default Prediction Using Network Based Features

Lorena Poenaru-Olaru; Judith Redi; Artur Hovanesyan; Huijuan Wang

doi:10.1007/978-3-030-93409-5_60

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 volume › Conference contribution › Scientific › peer-review

19 Downloads (Pure)

Abstract

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 language	English
Title of host publication	Complex Networks and Their Applications X
Subtitle of host publication	Proceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1
Editors	Rosa Maria Benito, Chantal Cherifi, Hocine Cherifi, Esteban Moro, Luis M. Rocha, Marta Sales-Pardo
Place of Publication	Cham
Publisher	Springer
Pages	732-743
Number of pages	12
Edition	1
ISBN (Electronic)	978-3-030-93409-5
ISBN (Print)	978-3-030-93411-8
DOIs	https://doi.org/10.1007/978-3-030-93409-5_60
Publication status	Published - 2022
Event	10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021 - Hybrid at Madrid, Spain Duration: 30 Nov 2021 → 2 Dec 2021 Conference number: 10th

Publication series

Name	Studies in Computational Intelligence
Publisher	Springer
Volume	1015
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

Conference

Conference	10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021
Country/Territory	Spain
City	Hybrid at Madrid
Period	30/11/21 → 2/12/21

Bibliographical note

Accepted author manuscript

Keywords

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-93409-5_60

default_prediction_using_network_featuresAccepted author manuscript, 257 KB

Cite this

Poenaru-Olaru, L., Redi, J., Hovanesyan, A., & Wang, H. (2022). Default Prediction Using Network Based Features. In R. M. Benito, C. Cherifi, H. Cherifi, E. Moro, L. M. Rocha, & M. Sales-Pardo (Eds.), Complex Networks and Their Applications X : Proceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1 (1 ed., pp. 732-743). (Studies in Computational Intelligence; Vol. 1015). Springer. https://doi.org/10.1007/978-3-030-93409-5_60

Poenaru-Olaru, Lorena ; Redi, Judith ; Hovanesyan, Artur ; Wang, Huijuan. / Default Prediction Using Network Based Features. Complex Networks and Their Applications X : Proceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1. editor / Rosa Maria Benito ; Chantal Cherifi ; Hocine Cherifi ; Esteban Moro ; Luis M. Rocha ; Marta Sales-Pardo. 1. ed. Cham : Springer, 2022. pp. 732-743 (Studies in Computational Intelligence).

@inproceedings{e088c64a18a946aaa232d5d27bd04486,

title = "Default Prediction Using Network Based Features",

abstract = "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.",

keywords = "Default prediction, Network centrality, Network features, Network-based models, Transactional network",

author = "Lorena Poenaru-Olaru and Judith Redi and Artur Hovanesyan and Huijuan Wang",

note = "Accepted author manuscript; 10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021 ; Conference date: 30-11-2021 Through 02-12-2021",

year = "2022",

doi = "10.1007/978-3-030-93409-5_60",

language = "English",

isbn = "978-3-030-93411-8",

series = "Studies in Computational Intelligence",

publisher = "Springer",

pages = "732--743",

editor = "Benito, {Rosa Maria} and Chantal Cherifi and Hocine Cherifi and Esteban Moro and Rocha, {Luis M.} and Marta Sales-Pardo",

booktitle = "Complex Networks and Their Applications X",

edition = "1",

}

Poenaru-Olaru, L, Redi, J, Hovanesyan, A & Wang, H 2022, Default Prediction Using Network Based Features. in RM Benito, C Cherifi, H Cherifi, E Moro, LM Rocha & M Sales-Pardo (eds), Complex Networks and Their Applications X : Proceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1. 1 edn, Studies in Computational Intelligence, vol. 1015, Springer, Cham, pp. 732-743, 10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021, Hybrid at Madrid, Spain, 30/11/21. https://doi.org/10.1007/978-3-030-93409-5_60

Default Prediction Using Network Based Features. / Poenaru-Olaru, Lorena; Redi, Judith; Hovanesyan, Artur; Wang, Huijuan.

Complex Networks and Their Applications X : Proceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1. ed. / Rosa Maria Benito; Chantal Cherifi; Hocine Cherifi; Esteban Moro; Luis M. Rocha; Marta Sales-Pardo. 1. ed. Cham : Springer, 2022. p. 732-743 (Studies in Computational Intelligence; Vol. 1015).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Default Prediction Using Network Based Features

AU - Poenaru-Olaru, Lorena

AU - Redi, Judith

AU - Hovanesyan, Artur

AU - Wang, Huijuan

N1 - Conference code: 10th

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - Default prediction

KW - Network centrality

KW - Network features

KW - Network-based models

KW - Transactional network

UR - http://www.scopus.com/inward/record.url?scp=85122496917&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-93409-5_60

DO - 10.1007/978-3-030-93409-5_60

M3 - Conference contribution

AN - SCOPUS:85122496917

SN - 978-3-030-93411-8

T3 - Studies in Computational Intelligence

SP - 732

EP - 743

BT - Complex Networks and Their Applications X

A2 - Benito, Rosa Maria

A2 - Cherifi, Chantal

A2 - Cherifi, Hocine

A2 - Moro, Esteban

A2 - Rocha, Luis M.

A2 - Sales-Pardo, Marta

PB - Springer

CY - Cham

T2 - 10th International Conference on Complex Networks and Their Applications, COMPLEX NETWORKS 2021

Y2 - 30 November 2021 through 2 December 2021

ER -

Poenaru-Olaru L, Redi J, Hovanesyan A, Wang H. Default Prediction Using Network Based Features. In Benito RM, Cherifi C, Cherifi H, Moro E, Rocha LM, Sales-Pardo M, editors, Complex Networks and Their Applications X : Proceedings of the 10th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2021, Volume 1. 1 ed. Cham: Springer. 2022. p. 732-743. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-030-93409-5_60

Default Prediction Using Network Based Features

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this