MetaRisk: Semi-supervised few-shot operational risk classification in banking industry

Zhang, Fan; Qi, Xiuxiu; Xiao, Chunjing; Wang, Jiahao

doi:10.1016/j.ins.2020.11.027

Cited by 10 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Fig. 1, as the default records (negative) are small samples in practical scenarios, the data distribution is imbalanced, which may lead to the unequal cost of misclassification errors and scarce accuracy of prediction [9,10]. In general, the missing values and skewed data distribution pose a huge challenge for default risk prediction.…”

Section: Introductionmentioning

confidence: 99%

Multi-view GCN for loan default risk prediction

Li,

Chen,

Wang

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

As a significant application of machine learning in financial scenarios, loan default risk prediction aims to evaluate the client’s default probability. However, most existing deep learning solutions treat each application as an independent individual, neglecting the explicit connections among different application records. Besides, these attempts suffer from the problem of missing data and imbalanced distribution (i.e., the default records are small samples against all the applications). We believe similar records could provide some auxiliary signals, which are of critical importance to alleviate the data missing issue and facilitate data argumentation. To this end, we propose multi-view loan application graphs, dubbed MLAGs. By evaluating the similarity between the records, a loan application graph can be constructed. Furthermore, we arrange different similarity thresholds to organize various graph structures for multi-graph constructions; thus, a variety of representations can be generated via information propagation and aggregation for small sample argumentation. Consequently, the imbalanced data distribution and missing values issues can be alleviated effectively. We conduct experiments on three public datasets from real-world home credit and P2P lending platforms, which show that MGCN outperforms both conventional and deep learning models. Ablation studies also illustrated the validity of each module design.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-view GCN for loan default risk prediction

Li,

Chen,

Wang

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…To overcome these issues, inspired by DivideMix [26] and semi-supervised prototype networks (ProNets) [27], based on the co-teaching framework, a method based on twin ProNets with noisy label self-correction (TProNet-NLSC) was proposed to address fault diagnosis for WT gearboxes with noisy labels. The main contributions of this study are summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

Twin prototype networks with noisy label self-correction for fault diagnosis of wind turbine gearboxes

Liu¹,

Tang²,

Li³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Deep strong-supervised learning-based methods have been widely used and have made significant progress in intelligent fault diagnosis for wind turbine (WT) gearboxes. The superior performance of such methods relies on high-quality labels. However, correctly labeling the data is challenging because of the complexity of fault vibration signals and fault modes in real industrial scenarios, resulting in noisy labels in datasets, which significantly restricts the application of strong-supervised fault diagnosis models. In this study, a method based on twin prototype networks with noisy label self-correction was proposed to address fault diagnosis for WT gearboxes with noisy labels. This method introduced a collaborative learning architecture to improve the confirmation bias in the self-training of individual networks and to slow the speed of learning noisy-labeled samples. Simultaneously, the loss distribution of the samples from each network was modeled using the Gaussian mixture model to dynamically identify mislabeled samples in the training dataset. Finally, a collaborative relabeling prototype refinement module was designed to optimize the prototype learning process and enable self-correction of noisy labels. The experiments demonstrated the effectiveness and superiority of the proposed method.

show abstract