English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurately credit default prediction faces challenges due to imbalanced dataand low correlation between features and labels. Existing default predictionstudies on the basis of gradient boosting decision trees (GBDT), deep learningtechniques, and feature selection strategies can have varying degrees ofsuccess depending on the specific task. Motivated by this, we proposeTab-Attention, a novel self-attention-based stacked generalization method forcredit default prediction. This approach ensembles the potential proprietaryknowledge contributions from multi-view feature spaces, to cope with lowfeature correlation and imbalance. We organize multi-view feature spacesaccording to the latent linear or nonlinear strengths between features andlabels. Meanwhile, the f1 score assists the model in imbalance training to findthe optimal state for identifying minority default samples. Our Tab-Attentionachieves superior Recall_1 and f1_1 of default intention recognition thanexisting GBDT-based models and advanced deep learning by about 32.92% and16.05% on average, respectively, while maintaining outstanding overallperformance and prediction performance for non-default samples. The proposedmethod could ensemble essential knowledge through the self-attention mechanism,which is of great significance for a more robust future prediction system.

Tab-Attention: Self-Attention-based Stacked Generalization for Imbalanced Credit Default Prediction