Authors: Mengran Zhu, Ye Zhang, Yulu Gong, Kaijuan Xing, Xu Yan, Jintong Song

Published on: February 28, 2024

Impact Score: 7.2

Arxiv code: Arxiv:2402.17979

Summary

• What is new: Introduction of an Ensemble Methods framework comprising LightGBM, XGBoost, and LocalEnsemble to significantly improve credit default prediction accuracy.
• Why this is important: The need for more accurate credit default predictions in consumer lending to enhance risk mitigation and lending decision optimization.
• What the research proposes: An innovative Ensemble Methods framework utilizing LightGBM, XGBoost, and LocalEnsemble modules to tackle identified limitations and set new accuracy benchmarks.
• Results: Experimental findings demonstrate the ensemble model’s superior effectiveness on the dataset, making substantial contributions to credit default prediction accuracy.

Technical Details

Technological frameworks used: Ensemble Methods

Models used: LightGBM, XGBoost, LocalEnsemble

Data used: nan

Potential Impact

Consumer lending industry, financial institutions focusing on credit risk management.

Want to implement this idea in a business?

We have generated a startup concept here: PredictEase.