Understanding Default Behavior in Online Lending

Yang, Yang; Xu, Yuhong; Wang, Chunping; Sun, Yizhou; Wu, Fei; Zhuang, Yueting; Gu, Min

doi:10.1145/3357384.3358052

Cited by 10 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pinjaman online yang diberikan tanpa agunan, dilakukan dengan internet, melalui proses aplikasi online yang mudah dan pendanaan yang cepat serta tingkat pengembalian yang menarik bagi pemberi pinjaman individu, tetapi memiliki tantangan tersendiri terkait manajemen risiko yang dihadapi (Yang et al, 2019…”

Section: Pendahuluanunclassified

“…Namun ada tantangan yang harus menjadi pertimbangan yaitu risiko, dimana sipeminjam seharusnya bisa mengelola setiap risiko peminjaman dengan menyeimbangkan biaya pinjaman dan biaya pengembaliannya. (Yang et al, 2019) Hasil penelitian menunjukkan bahwa jika literasi keuangan digital signifikan dalam menjelaskan preferensi risiko dan prilaku keuangan, tetapi literasi keuangan digital tidak berpengaruh terhadap prilaku keuangan pinjaman online.…”

Section: Simpulan Kesimpulanunclassified

See 1 more Smart Citation

Mengukur Prilaku Pinjaman Online Melalui Literasi Keuangan Digital, Preferensi Risiko dan Faktor Demografi Sebagai Variabel Moderasi

Maivalinda,

Sulistianingsih,

Riski

2023

JEBD

View full text Add to dashboard Cite

This study aims to measure the financial behavior of online loans through digital financial literacy variables, risk preferences and demographic factors. This research also looks at the positive interaction of digital financial literacy with financial behavior and risk preference with financial behavior and demographic factors as a moderation. The number of samples was selected using the convenience sampling method. The analytical method uses Structural Equation Modeling Partial Least Square (SEM PLS) analysis. The results of this study conclude that digital financial literacy and demographic factors have a significant effect on online loan financial behavior. Digital financial literacy has a significant effect on online loan financial behavior but demographic factors do not affect risk preference. Likewise, risk preference has no effect on online loan financial behavior. Demographic factors moderate digital financial literacy and financial behavior but demographic factors do not moderate risk preferences for online loan financial behavior. ABSTRAK Penelitian ini bertujuan untuk mengukur prilaku keuangan pinjaman online melalui variabel variabel literasi keuangan digital, preferensi risiko dan faktor demografi. Penelitian ini juga melihat interaksi positif dari literasi keuangan digital dengan prilaku keuangan dan preferensi risiko dengan prilaku keuangan dengan faktor demografi sebagai moderasinya. Jumlah sampel dipilih dengan menggunakan metode convenience sampling. Metode analisis menggunakan analisis Structural Equation Modelling Partial Least Square (SEM PLS). Hasil penelitian ini menyimpulkan bahwa literasi keuangan digital dan faktor demografi berpengaruh signifikan terhadap prilaku keuangan pinjaman online. Literasi keuangan digital berpengaruh signifikan terhadap prilaku keuangan pinjaman online tetapi faktor demografi tidak berpengaruh terhadap preferensi risiko. Demikian juga preferensi risiko tidak berpengaruh terhadap prilaku keuangan pinjaman online. Faktor demografi memoderasi literasi keuangan digital dan perilaku keuangan namun faktor demografi tidak memoderasi preferensi risiko terhadap prilaku keuangan pinjaman online.

show abstract

Section: Pendahuluanunclassified

Section: Simpulan Kesimpulanunclassified

Mengukur Prilaku Pinjaman Online Melalui Literasi Keuangan Digital, Preferensi Risiko dan Faktor Demografi Sebagai Variabel Moderasi

Maivalinda,

Sulistianingsih,

Riski

2023

JEBD

View full text Add to dashboard Cite

show abstract

“…However, unlike traditional loan services, in online credit services, users are not required to provide pledge or previous loan information. And most users are new and have no previous records in the online platform, e.g., 60% of the users have no previous loan records in PPDai, an online lending platform in China [4]. In this way, users', especially new users' own features are very sparse, which poses a great challenge for previous methods to work well.…”

Section: Introductionmentioning

confidence: 99%

Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning

Wang¹,

Zhang²,

Zhao³

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

User financial default prediction plays a critical role in credit risk forecasting and management. It aims at predicting the probability that the user will fail to make the repayments in the future. Previous methods mainly extract a set of user individual features regarding his own profiles and behaviors and build a binary-classification model to make default predictions. However, these methods cannot get satisfied results, especially for users with limited information. Although recent efforts suggest that default prediction can be improved by social relations, they fail to capture the higher-order topology structure at the level of small subgraph patterns. In this paper, we fill in this gap by proposing a motif-preserving Graph Neural Network with curriculum learning (MotifGNN) to jointly learn the lower-order structures from the original graph and higherorder structures from multi-view motif-based graphs for financial default prediction. Specifically, to solve the problem of weak connectivity in motif-based graphs, we design the motif-based gating mechanism. It utilizes the information learned from the original graph with good connectivity to strengthen the learning of the higher-order structure. And considering that the motif patterns of different samples are highly unbalanced, we propose a curriculum learning mechanism on the whole learning process to more focus on the samples with uncommon motif distributions. Extensive experiments on one public dataset and two industrial datasets all demonstrate the effectiveness of our proposed method.

show abstract

“…Traditional fraud user detection relies heavily on borrowers' historical loan records. But, a large portion of borrowers miss such information (Yang et al 2019b), especially for the new borrowers which could result in cold-start issues. Fortunately, there are some other data sources available, which reveal clues regarding one customer's fraud probability.…”

Section: Introductionmentioning

confidence: 99%

Loan Fraud Users Detection in Online Lending Leveraging Multiple Data Views

Zhao

Huang

Chen³

et al. 2023

AAAI

View full text Add to dashboard Cite

In recent years, online lending platforms have been becoming attractive for micro-financing and popular in financial industries. However, such online lending platforms face a high risk of failure due to the lack of expertise on borrowers' creditworthness. Thus, risk forecasting is important to avoid economic loss. Detecting loan fraud users in advance is at the heart of risk forecasting. The purpose of fraud user (borrower) detection is to predict whether one user will fail to make required payments in the future. Detecting fraud users depend on historical loan records. However, a large proportion of users lack such information, especially for new users. In this paper, we attempt to detect loan fraud users from cross domain heterogeneous data views, including user attributes, installed app lists, app installation behaviors, and app-in logs, which compensate for the lack of historical loan records. However, it is difficult to effectively fuse the multiple heterogeneous data views. Moreover, some samples miss one or even more data views, increasing the difficulty in fusion. To address the challenges, we propose a novel end-to-end deep multiview learning approach, which encodes heterogeneous data views into homogeneous ones, generates the missing views based on the learned relationship among all the views, and then fuses all the views together to a comprehensive view for identifying fraud users. Our model is evaluated on a real-world large-scale dataset consisting of 401,978 loan records of 228,117 users from January 1, 2019, to September 30, 2019, achieving the state-of-the-art performance.

show abstract

Understanding Default Behavior in Online Lending

Cited by 10 publications

References 18 publications

Mengukur Prilaku Pinjaman Online Melalui Literasi Keuangan Digital, Preferensi Risiko dan Faktor Demografi Sebagai Variabel Moderasi

Mengukur Prilaku Pinjaman Online Melalui Literasi Keuangan Digital, Preferensi Risiko dan Faktor Demografi Sebagai Variabel Moderasi

Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning

Loan Fraud Users Detection in Online Lending Leveraging Multiple Data Views

Contact Info

Product

Resources

About