Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning

作者：

Highlights：

• This study uses the new machine learning algorithms to predict the default risk.

• Two different ways to clean too many variables and missing values data.

• Comparisons are made between these two equally sophisticated algorithms.

• Put forward relevant policy recommendations for global P2P platforms.

摘要

•This study uses the new machine learning algorithms to predict the default risk.•Two different ways to clean too many variables and missing values data.•Comparisons are made between these two equally sophisticated algorithms.•Put forward relevant policy recommendations for global P2P platforms.

论文关键词：P2P,Data cleaning,Default rate,LightGBM algorithm,XGboost algorithm

论文评审过程：Received 7 February 2018, Revised 24 June 2018, Accepted 2 August 2018, Available online 3 August 2018, Version of Record 28 August 2018.

论文官网地址：https://doi.org/10.1016/j.elerap.2018.08.002