A PSO-based ensemble model for peer-to-peer credit scoring

Chaoqun Wang; Zhongyi Hu; Raymond Chiong; Sandeep Dhakal; Xuan Cheng; Yukun Bao

doi:10.1109/FSKD.2018.8687154

A PSO-based ensemble model for peer-to-peer credit scoring

Chaoqun Wang
, Zhongyi Hu
, Raymond Chiong
, Sandeep Dhakal
, Xuan Cheng
, Yukun Bao

School of Science & Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

We propose a multi-classifier ensemble model based on particle swarm optimization (PSO) for the evaluation of personal credit risk in peer-to-peer (P2P) lending platforms. In the proposed method, we consider the differences and complementarity of the base classifiers' performance and use PSO to optimize their weights. Experimental results show that our proposed P2P personal credit scoring model outperforms both single and other benchmark ensemble models. Among the examined model variants, the ensemble model based on PSO with 100 particles is the best.

Original language	English
Title of host publication	ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
Place of Publication	United States of America
Publisher	IEEE
Pages	412-418
ISBN (Print)	9781538680971, 9781538680964, 9781538680988
DOIs	https://doi.org/10.1109/FSKD.2018.8687154
Publication status	Published - 2018
Event	ICNC-FSKD 2018: 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery - Huangshan, China Duration: 28 Jul 2018 → 30 Jul 2018

Conference

Conference	ICNC-FSKD 2018: 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
Country/Territory	China
City	Huangshan
Period	28/07/18 → 30/07/18

Access to Document

10.1109/FSKD.2018.8687154

https://hdl.handle.net/1959.11/61442

Handle.net

Persistent link

Cite this

@inproceedings{8079799b0c054ba7920608db86f729b2,

title = "A PSO-based ensemble model for peer-to-peer credit scoring",

abstract = "We propose a multi-classifier ensemble model based on particle swarm optimization (PSO) for the evaluation of personal credit risk in peer-to-peer (P2P) lending platforms. In the proposed method, we consider the differences and complementarity of the base classifiers' performance and use PSO to optimize their weights. Experimental results show that our proposed P2P personal credit scoring model outperforms both single and other benchmark ensemble models. Among the examined model variants, the ensemble model based on PSO with 100 particles is the best.",

author = "Chaoqun Wang and Zhongyi Hu and Raymond Chiong and Sandeep Dhakal and Xuan Cheng and Yukun Bao",

year = "2018",

doi = "10.1109/FSKD.2018.8687154",

language = "English",

isbn = "9781538680971",

pages = "412--418",

booktitle = "ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery",

publisher = "IEEE",

note = "ICNC-FSKD 2018: 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery ; Conference date: 28-07-2018 Through 30-07-2018",

}

Wang, C, Hu, Z, Chiong, R, Dhakal, S, Cheng, X & Bao, Y 2018, A PSO-based ensemble model for peer-to-peer credit scoring. in ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery. IEEE, United States of America, pp. 412-418, ICNC-FSKD 2018: 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, Huangshan, China, 28/07/18. https://doi.org/10.1109/FSKD.2018.8687154

A PSO-based ensemble model for peer-to-peer credit scoring. / Wang, Chaoqun; Hu, Zhongyi; Chiong, Raymond et al.
ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery. United States of America: IEEE, 2018. p. 412-418.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A PSO-based ensemble model for peer-to-peer credit scoring

AU - Wang, Chaoqun

AU - Hu, Zhongyi

AU - Chiong, Raymond

AU - Dhakal, Sandeep

AU - Cheng, Xuan

AU - Bao, Yukun

PY - 2018

Y1 - 2018

N2 - We propose a multi-classifier ensemble model based on particle swarm optimization (PSO) for the evaluation of personal credit risk in peer-to-peer (P2P) lending platforms. In the proposed method, we consider the differences and complementarity of the base classifiers' performance and use PSO to optimize their weights. Experimental results show that our proposed P2P personal credit scoring model outperforms both single and other benchmark ensemble models. Among the examined model variants, the ensemble model based on PSO with 100 particles is the best.

AB - We propose a multi-classifier ensemble model based on particle swarm optimization (PSO) for the evaluation of personal credit risk in peer-to-peer (P2P) lending platforms. In the proposed method, we consider the differences and complementarity of the base classifiers' performance and use PSO to optimize their weights. Experimental results show that our proposed P2P personal credit scoring model outperforms both single and other benchmark ensemble models. Among the examined model variants, the ensemble model based on PSO with 100 particles is the best.

U2 - 10.1109/FSKD.2018.8687154

DO - 10.1109/FSKD.2018.8687154

M3 - Conference contribution

SN - 9781538680971

SN - 9781538680964

SN - 9781538680988

SP - 412

EP - 418

BT - ICNC-FSKD 2018 - 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

PB - IEEE

CY - United States of America

T2 - ICNC-FSKD 2018: 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

Y2 - 28 July 2018 through 30 July 2018

ER -

A PSO-based ensemble model for peer-to-peer credit scoring

Abstract

Conference

Access to Document

Handle.net

Fingerprint

Cite this