Peer to peer lending risk analysis based on embedded technique and stacking ensemble learning

Peer to peer lending is famous for easy and fast loans from complicated traditional institutions. Therefore, big data machine learning are needed credit risk analysis, especially potential defaulters. However, imbalance high computation have a terrible effect on prediction performance. This paper proposes stacking ensemble with features selection based embedded techniques (gradient boosted trees (GBDT), random forest (RF), adaptive boosting (AdaBoost), extra gradient (XGBoost), light (LGBM), decision tree (DT)) predict the of individual borrowers (P2P) lending. The model created stack meta-learners used in feature selection. selection+ produces an average 94.54% accuracy 69.10 s execution time. RF meta-learner+Stacking best classification model, LGBM meta-learner+stacking fastest Based experimental results, this showed that P2P could be improved using addition proper