Comparative experimentson the GWO module utilizing across Taiwan Credit Default Data and Home Credit Default Risk Data. The evaluation metrics include Parameters (M), Floating Point Operations (FLOPs) (G), Inference Time (ms), and Training Duration (s).

<p>Comparative experimentson the GWO module utilizing across Taiwan Credit Default Data and Home Credit Default Risk Data. The evaluation metrics include Parameters (M), Floating Point Operations (FLOPs) (G), Inference Time (ms), and Training Duration (s).</p>

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Yetong Fang (21433414) (author)
منشور في:	2025
الموضوعات:	Ecology Science Policy Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified lendingclub loan dataset integrating advanced technologies innovative technical solution handling time dependencies grey wolf optimization experimental results show effectively capture patterns customer historical behaviors 65 %, rmse 0 %, 21 traditional method plawiak paper performs well optimizing key parameters dimensional financial data credit score prediction cnn performs well 51 %, 4 5 %, 68 limited prediction performance gwo model proposed 4 %, traditional methods paper proposes overall performance key component gwo algorithm financial industry financial field xlink "> significantly improving risk management hyperparameter tuning generalization ability fully capturing feature extraction existing methods digital transformation deep learning combines cnns
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

Comparative experimentson the GWO module utilizing across Taiwan Credit Default Data and Home Credit Default Risk Data. The evaluation metrics include Parameters (M), Floating Point Operations (FLOPs) (G), Inference Time (ms), and Training Duration (s).

مواد مشابهة