Incorporating Feature Interactions and Contrastive Learning for Credit Prediction

Incorporating Feature Interactions and Contrastive Learning for Credit Prediction

The efficacy of credit risk assessment models is pivotal to the risk management capacity of financial institutions. Traditional credit risk models often suffer from inadequate predictive accuracy due to overlooked feature combinations and weak supervisory signals. Addressing these limitations, we pr...

Full beskrivning

Bibliografiska uppgifter
Huvudupphovsmän: Lisi Zhang, Qiancheng Yu, Beijing Zhou, Yifan Zhang, Zhiyong Hu
Materialtyp: Artikel
Språk:English
Publicerad: IEEE 2023-01-01
Serie:IEEE Access
Ämnen:
Credit appraisal
second-order crossover
attention mechanisms
deep neural networks
contrastive learning
Länkar:https://ieeexplore.ieee.org/document/10273718/

Internet

https://ieeexplore.ieee.org/document/10273718/

Liknande verk