New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*

Peer-to-peer (P2P) Lending is a type of financial innovation that offers loans without intermediaries to individuals and companies. In the P2P lending system, there is a risk of default on the loan which causes the company to lose. Many studies have to reduce the risk of default by developing a clas...

Full description

Saved in:
Bibliographic Details
Main Authors: Much Aziz Muslim, Much Aziz Muslim, Tiara Lailatul Nikmah, Tiara Lailatul Nikmah, Dwika Ananda Agustina Pertiwi, Dwika Ananda Agustina Pertiwi, Subhan, Subhan, Jumanto, Jumanto, Yosza Dasril, Yosza Dasril, Iswanto, Iswanto
Format: Article
Language:English
Published: Elsevier 2023
Subjects:
Online Access:http://eprints.uthm.edu.my/10253/1/J15821_5f1a59ce0a954378b7ec3d794c31ab57.pdf
http://eprints.uthm.edu.my/10253/
https://doi.org/10.1016/j.iswa.2023.200204
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uthm.eprints.10253
record_format eprints
spelling my.uthm.eprints.102532023-10-30T07:13:18Z http://eprints.uthm.edu.my/10253/ New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning* Much Aziz Muslim, Much Aziz Muslim Tiara Lailatul Nikmah, Tiara Lailatul Nikmah Dwika Ananda Agustina Pertiwi, Dwika Ananda Agustina Pertiwi Subhan, Subhan Jumanto, Jumanto Yosza Dasril, Yosza Dasril Iswanto, Iswanto T Technology (General) Peer-to-peer (P2P) Lending is a type of financial innovation that offers loans without intermediaries to individuals and companies. In the P2P lending system, there is a risk of default on the loan which causes the company to lose. Many studies have to reduce the risk of default by developing a classification model of prediction of default that focuses on increasing accuracy. However, the big problem with prediction is data imbalance and low performance classification algorithms. The purpose of this study is to improve the accuracy of default risk prediction by balancing the data and combining the stacking model ensemble with the meta-learner. The proposed new model consists of 3 optimization parts, the first is Synthetic Minority Oversampling Technique (SMOTE), the second is the selection of features and the third is stacking ensemble learning. The SMOTE method is used to balance the data, the feature selection LightGBM and stacking ensemble learning (LGBFS-StackingXGBoost) to optimize machine learning accuracy. A new model of stacking ensemble learning by combining three base-learner algorithms namely KNN, SVM and Random Forest into the XGBoost meta-learner algorithm. The model was tested using two datasets, namely the online P2P lending dataset and the lending club loan data analysis dataset. The evaluation results show that LGBFS-StackingXGBoost is the best model for both datasets. In the online P2P lending dataset, it received an accuracy of 99,982% and in the lending club loan data analysis dataset, it received an accuracy of 91,434%. This study shows that the accuracy of the prediction model can be improved using the LGBFS-StackingXGBoost method. Elsevier 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/10253/1/J15821_5f1a59ce0a954378b7ec3d794c31ab57.pdf Much Aziz Muslim, Much Aziz Muslim and Tiara Lailatul Nikmah, Tiara Lailatul Nikmah and Dwika Ananda Agustina Pertiwi, Dwika Ananda Agustina Pertiwi and Subhan, Subhan and Jumanto, Jumanto and Yosza Dasril, Yosza Dasril and Iswanto, Iswanto (2023) New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*. Intelligent Systems with Applications, 18. pp. 1-8. https://doi.org/10.1016/j.iswa.2023.200204
institution Universiti Tun Hussein Onn Malaysia
building UTHM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tun Hussein Onn Malaysia
content_source UTHM Institutional Repository
url_provider http://eprints.uthm.edu.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Much Aziz Muslim, Much Aziz Muslim
Tiara Lailatul Nikmah, Tiara Lailatul Nikmah
Dwika Ananda Agustina Pertiwi, Dwika Ananda Agustina Pertiwi
Subhan, Subhan
Jumanto, Jumanto
Yosza Dasril, Yosza Dasril
Iswanto, Iswanto
New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*
description Peer-to-peer (P2P) Lending is a type of financial innovation that offers loans without intermediaries to individuals and companies. In the P2P lending system, there is a risk of default on the loan which causes the company to lose. Many studies have to reduce the risk of default by developing a classification model of prediction of default that focuses on increasing accuracy. However, the big problem with prediction is data imbalance and low performance classification algorithms. The purpose of this study is to improve the accuracy of default risk prediction by balancing the data and combining the stacking model ensemble with the meta-learner. The proposed new model consists of 3 optimization parts, the first is Synthetic Minority Oversampling Technique (SMOTE), the second is the selection of features and the third is stacking ensemble learning. The SMOTE method is used to balance the data, the feature selection LightGBM and stacking ensemble learning (LGBFS-StackingXGBoost) to optimize machine learning accuracy. A new model of stacking ensemble learning by combining three base-learner algorithms namely KNN, SVM and Random Forest into the XGBoost meta-learner algorithm. The model was tested using two datasets, namely the online P2P lending dataset and the lending club loan data analysis dataset. The evaluation results show that LGBFS-StackingXGBoost is the best model for both datasets. In the online P2P lending dataset, it received an accuracy of 99,982% and in the lending club loan data analysis dataset, it received an accuracy of 91,434%. This study shows that the accuracy of the prediction model can be improved using the LGBFS-StackingXGBoost method.
format Article
author Much Aziz Muslim, Much Aziz Muslim
Tiara Lailatul Nikmah, Tiara Lailatul Nikmah
Dwika Ananda Agustina Pertiwi, Dwika Ananda Agustina Pertiwi
Subhan, Subhan
Jumanto, Jumanto
Yosza Dasril, Yosza Dasril
Iswanto, Iswanto
author_facet Much Aziz Muslim, Much Aziz Muslim
Tiara Lailatul Nikmah, Tiara Lailatul Nikmah
Dwika Ananda Agustina Pertiwi, Dwika Ananda Agustina Pertiwi
Subhan, Subhan
Jumanto, Jumanto
Yosza Dasril, Yosza Dasril
Iswanto, Iswanto
author_sort Much Aziz Muslim, Much Aziz Muslim
title New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*
title_short New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*
title_full New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*
title_fullStr New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*
title_full_unstemmed New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning*
title_sort new model combination meta-learner to improve accuracy prediction p2p lending with stacking ensemble learning*
publisher Elsevier
publishDate 2023
url http://eprints.uthm.edu.my/10253/1/J15821_5f1a59ce0a954378b7ec3d794c31ab57.pdf
http://eprints.uthm.edu.my/10253/
https://doi.org/10.1016/j.iswa.2023.200204
_version_ 1781707455827279872
score 13.160551