Improving Investment Suggestions for Peer-to-Peer Lending via Integrating Credit Scoring into Profit Scoring

Credit scoring has become an important issue because competition among financial institutions is intense and even a small improvement in predictive accuracy can result in significant savings. Financial institutions are looking for optimal strategies using credit scoring models. Therefore, credit scoring tools are extensively studied. As a result, various parametric statistical methods, non-parametric statistical tools and soft computing approaches have been developed to improve the accuracy of credit scoring models. In this paper, different approaches are used to classify customers into those who repay the loan and those who default on a loan. The purpose of this study is to investigate the performance of two credit scoring techniques, the logistic regression model estimated on categorized variables modified with the use of WOE (Weight of Evidence) transformation, and neural networks. We also combine multiple classifiers and test whether ensemble learning has better performance. To evaluate the feasibility and effectiveness of these methods, the analysis is performed on Lending Club data. In addition, we investigate Peer-to-peer lending, also called social lending. From the results, it can be concluded that the logistic regression model can provide better performance than neural networks. The proposed ensemble model (a combination of logistic regression and neural network by averaging the probabilities obtained from both models) has higher AUC, Gini coefficient and Kolmogorov-Smirnov statistics compared to other models. Therefore, we can conclude that the ensemble model allows to successfully reduce the potential risks of losses due to misclassification costs.

Get full-text (via PubEx)

Comparing Performance of Machine Learning Algorithms for Default Risk Prediction in Peer to Peer Lending

TEM Journal ◽

10.18421/tem101-16 ◽

2021 ◽

pp. 133-143

Author(s):

Yanka Aleksandrova

Keyword(s):

Machine Learning ◽

Default Risk ◽

Credit Scoring ◽

Learning Algorithms ◽

Peer To Peer ◽

Machine Learning Algorithms ◽

Ensemble Classifiers ◽

Peer Lending ◽

Official Site ◽

Heterogeneous Ensemble

The purpose of this research is to evaluate several popular machine learning algorithms for credit scoring for peer to peer lending. The dataset to fit the models is extracted from the official site of Lending Club. Several models have been implemented, including single classifiers (logistic regression, decision tree, multilayer perceptron), homogeneous ensembles (XGBoost, GBM, Random Forest) and heterogeneous ensemble classifiers like Stacked Ensembles. Results show that ensemble classifiers outperform single ones with Stacked Ensemble and XGBoost being the leaders.

Get full-text (via PubEx)

The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending

Decision Support Systems ◽

10.1016/j.dss.2016.06.014 ◽

2016 ◽

Vol 89 ◽

pp. 113-122 ◽

Cited By ~ 82

Author(s):

Carlos Serrano-Cinca ◽

Begoña Gutiérrez-Nieto

Keyword(s):

Credit Scoring ◽

Scoring Systems ◽

Peer To Peer ◽

P2p Lending ◽

Profit Scoring

Get full-text (via PubEx)

Fungsi Jaminan Sebagai Penentu Credit Scoring Dalam Layanan Pinjam Meminjam Uang Berbasis Teknologi Informasi

Jurist-Diction ◽

10.20473/jd.v4i5.29823 ◽

2021 ◽

Vol 4 (5) ◽

pp. 1871

Author(s):

Nalendra Pradipto

Keyword(s):

Information Technology ◽

Industrial Revolution ◽

Credit Scoring ◽

Peer To Peer ◽

The Public ◽

P2p Lending ◽

Risk Grade ◽

Peer Lending ◽

Financial Technology

AbstractThe growth of information technology or commonly referred to as Industrial Revolution 4.0 has given birth to a new idea namely Money Lending and Borrowing Services based on Information Technology. Peer to Peer Lending (P2P) Lending is a service that is much in demand by the public. The majority of P2P Lending financial technology providers do not require collateral. With this condition, OJK has issued a special regulation, namely POJK No. 77 / POJK.01 / 2016 concerning Money Lending and Borrowing Services based on Information Technology. Article 21 POJK No.77 / POJK.01/2016 states that the Operator is required to manage credit risk and operational risk. One risk management undertaken by the Provider is to use Credit Scoring to classify Debtors into certain risk grades. However, because the majority of P2P Lending does not require a material guarantee, the Credit Scoring factor other than collateral becomes very important. In practice, the Operator is often less selective about the classification of Debtors in Credit Scoring, resulting in many defaults.Keywords: Peer to Peer Lending; Financial Technology; Credit Scoring; Risk Grade.AbstrakPerkembangan teknologi informasi informasi atau yang biasa disebut dengan Revolusi Industri 4.0 telah melahirkan gagasan baru yaitu Layanan Meminjam Uang Berbasis Teknologi Informasi. Peer to Peer Lending (P2P) Lending menjadi layanan yang banyak diminati oleh masyarakat. Dari beragam Penyelenggara teknologi finansial P2P Lending mayoritas tidak mensyaratkan adanya jaminan kebendaan. Dengan adanya kondisi tersebut OJK telah mengeluarkan aturan khusus yaitu POJK No. 77/POJK.01/2016 tentang Layanan Pinjam Meminjam Uang Berbasis Teknologi Informasi. Pasal 21 POJK No.77/POJK.01/2016 menyatakan Penyelenggara wajib melakukan manajemen risiko kredit dan risiko operasional. Salah satu manajemen risiko yang dilakukan Penyelenggara adalah menggunakan Credit Scoring untuk mengklasifikasi Debitor ke dalam risk grade tertentu. Meskipun demikian karena mayoritas P2P Lending tidak mensyaratkan adanya jaminan kebendaan, maka faktor Credit Scoring selain jaminan menjadi sangat penting. Pada prakteknya Penyelenggara seringkali kurang selektif terhadap klasifikasi Debitor dalam Credit Scoring sehingga banyak terjadi wanprestasi. Kata Kunci: Peer to Peer Lending; Teknologi Finansial; Credit Scoring; Risk Grade.

Get full-text (via PubEx)

Research on Credit Scoring by Fusing Social Media Information in Online Peer-to-Peer Lending

Procedia Computer Science ◽

10.1016/j.procs.2016.07.055 ◽

2016 ◽

Vol 91 ◽

pp. 168-174 ◽

Cited By ~ 23

Author(s):

Yuejin Zhang ◽

Hengyue Jia ◽

Yunfei Diao ◽

Mo Hai ◽

Haifeng Li

Keyword(s):

Social Media ◽

Credit Scoring ◽

Peer To Peer ◽

Peer Lending

Get full-text (via PubEx)

Minimalisasi Risiko Kredit (NPL) Pada Fintach Peer to Peer Lending melalui Kewajiban Pelaporan SLIK OJK

Jurnal Ilmiah Mandala Education ◽

10.36312/jime.v6i2.1401 ◽

2020 ◽

Vol 6 (2) ◽

Author(s):

Renova Hutapea

Keyword(s):

Credit Scoring ◽

Peer To Peer ◽

Peer Lending

Perkembangan dari Fintech peer to peer lending di Indonesia sangat pesat dalam mendukung peningkatan inklusi keuangan. Seiring dengan peningkatan nilai pinjaman yang disalurkan melalui fintech peer to peer lending, ratio kredit NPL juga terus meningkat. Untuk itu fungsi pengawasan dari Otoritas Jasa Keuangan (OJK) sangat penting terhadap perkembangan dari pelaksanaan penyaluran pinjaman yang dilakukan oleh penyelenggara peer to peer lending yang telah terdaftar dan berizin di OJK. Adapun metode penelitian yang digunakan adalah metode penelitian hukum normatif, yang akan melakukan penelitian terhadap berbagai aturan hukum yang terkait. Metode penelitian hukum adalah metode yang mengacu pada hukum dan peraturan perundang-undangan yang berlaku dengan pendekatan analitis. Hasil dari satu penelitian ini adalah salah satu upaya meminimalisasi peningkatan risiko kredit (NPL) pada industri fintech peer to peer lending yaitu dengan melakukan tindakan preventif yang efekfif melalui penilaian karakter calon penerima pinjaman dari informasi perkreditan yang diperoleh pada Sistem Layanan Informasi Keuangan (SLIK). Oleh karenanya, sebagai bentuk pengawasan dari OJK terhadap industri fintech peer to peer lending dibutuhkan pengaturan mengenai kewajiban pelaporan bagi setiap penyelenggara fintech lending pada SLIK sehingga dengan akses informasi perkreditan yang komprehensif dapat memberikan proses credit scoring yang lebih baik dan akurat demi terjaganya kualitas dari pinjaman yang disalurkan.

Get full-text (via PubEx)