Wide and deep learning for peer-to-peer lending

J 2019

Wide and deep learning for peer-to-peer lending

BASTANI, Kaveh; Elham ASGARI a Hamed NAMAVARI

Základní údaje

Originální název

Wide and deep learning for peer-to-peer lending

Autoři

BASTANI, Kaveh; Elham ASGARI a Hamed NAMAVARI

Vydání

Expert Systems with Applications, OXFORD, Elsevier, 2019, 0957-4174

Další údaje

Typ výsledku

Článek v odborném periodiku

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 5.452

Označené pro přenos do RIV

DOI

https://doi.org/10.1016/j.eswa.2019.05.042

UT WoS

000475997000018

Klíčová slova anglicky

Wide and deep learning; Peer-to-peer lending; Credit scoring; Profit scoring

Změněno: 29. 6. 2023 08:19, Oleg Deev, Ph.D.

Anotace

V originále

This paper proposes a two-stage scoring approach to help lenders decide their fund allocations in peerto-peer (P2P) lending market. The existing scoring approaches focus on only either probability of default (PD) prediction, known as credit scoring, or profitability prediction, known as profit scoring, to identify the best loans for investment. Credit scoring fails to deliver the main need of lenders on how much profit they may obtain through their investment. On the other hand, profit scoring can satisfy that need by predicting the investment profitability. However, profit scoring is not free from the imbalance problem where most of the past loans are non-default. Consequently, ignorance of the imbalance problem significantly affects the accuracy of profitability prediction. Our proposed two-stage scoring approach is an integration of credit scoring and profit scoring to address the above challenges. More specifically, stage 1 is designed to identify non-default loans while the imbalanced nature of loan status is considered in PD prediction. The loans identified as non-default are then moved to stage 2 for prediction of profitability, measured by internal rate of return. Wide and deep learning is used to build the predictive models in both stages to achieve both memorization and generalization. Extensive numerical studies are conducted based on real-world data to verify the effectiveness of the proposed approach. The numerical studies indicate our two-stage scoring approach outperforms the existing credit scoring and profit scoring approaches. (C) 2019 Elsevier Ltd. All rights reserved.

Citovat

BASTANI, Kaveh; Elham ASGARI a Hamed NAMAVARI. Wide and deep learning for peer-to-peer lending. Expert Systems with Applications. OXFORD: Elsevier, 2019, roč. 134, s. 209-224. ISSN 0957-4174. Dostupné z: https://doi.org/10.1016/j.eswa.2019.05.042.

@article{2294959,
   author = {Bastani, Kaveh and Asgari, Elham and Namavari, Hamed},
   article_location = {OXFORD},
   doi = {https://doi.org/10.1016/j.eswa.2019.05.042},
   keywords = {Wide and deep learning; Peer-to-peer lending; Credit scoring; Profit scoring},
   issn = {0957-4174},
   journal = {Expert Systems with Applications},
   title = {Wide and deep learning for peer-to-peer lending},
   volume = {134},
   year = {2019}
}

TY  - JOUR
ID  - 2294959
AU  - Bastani, Kaveh - Asgari, Elham - Namavari, Hamed
PY  - 2019
TI  - Wide and deep learning for peer-to-peer lending
JF  - Expert Systems with Applications
VL  - 134
SP  - 209-224
EP  - 209-224
PB  - Elsevier
SN  - 09574174
KW  - Wide and deep learning
KW  - Peer-to-peer lending
KW  - Credit scoring
KW  - Profit scoring
N2  - This paper proposes a two-stage scoring approach to help lenders decide their fund allocations in peerto-peer (P2P) lending market. The existing scoring approaches focus on only either probability of default (PD) prediction, known as credit scoring, or profitability prediction, known as profit scoring, to identify the best loans for investment. Credit scoring fails to deliver the main need of lenders on how much profit they may obtain through their investment. On the other hand, profit scoring can satisfy that need by predicting the investment profitability. However, profit scoring is not free from the imbalance problem where most of the past loans are non-default. Consequently, ignorance of the imbalance problem significantly affects the accuracy of profitability prediction. Our proposed two-stage scoring approach is an integration of credit scoring and profit scoring to address the above challenges. More specifically, stage 1 is designed to identify non-default loans while the imbalanced nature of loan status is considered in PD prediction. The loans identified as non-default are then moved to stage 2 for prediction of profitability, measured by internal rate of return. Wide and deep learning is used to build the predictive models in both stages to achieve both memorization and generalization. Extensive numerical studies are conducted based on real-world data to verify the effectiveness of the proposed approach. The numerical studies indicate our two-stage scoring approach outperforms the existing credit scoring and profit scoring approaches. (C) 2019 Elsevier Ltd. All rights reserved.
ER  -

BASTANI, Kaveh; Elham ASGARI a Hamed NAMAVARI. Wide and deep learning for peer-to-peer lending. \textit{Expert Systems with Applications}. OXFORD: Elsevier, 2019, roč.~134, s.~209-224. ISSN~0957-4174. Dostupné z: https://doi.org/10.1016/j.eswa.2019.05.042.

Přehled o publikaci