Risk assessment in social lending via random forests

作者：

Highlights：

• Social lending has emerged as a viable platform alternative to banks.

• Widespread adoption depends on better risk attribution to borrowers.

• A random forest (RF) based method is proposed for identifying good borrowers.

• Our results indicate RF outperforms traditional credit scoring methods.

摘要

•Social lending has emerged as a viable platform alternative to banks.•Widespread adoption depends on better risk attribution to borrowers.•A random forest (RF) based method is proposed for identifying good borrowers.•Our results indicate RF outperforms traditional credit scoring methods.

论文关键词：Peer-to-peer lending,Social lending,Risk assessment,Machine learning,Random forest

论文评审过程：Available online 13 February 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.02.001