Skip to main content

Table 3 Loan default classification comparison of credit and profit scoring models—Bondora

From: Default or profit scoring credit systems? Evidence from European and US peer-to-peer lending markets

Model Accuracy (%) Specificity (%) Sensitivity (%)
Panel A: Credit scoring models    
 LR 71.2 73.5 70.5
 \(LR^{{\lambda_{\min } ,\alpha = 1}}\) 71.4 73.5 70.7
 \(LR^{{\lambda_{\min } ,\alpha = 0}}\) 70.9 73.7 70.0
 \(LR^{{\lambda_{\min } ,\alpha_{\min } }}\) 71.0 73.0 70.3
 RFC 78.8 56.2 86.1
 NNC 67.9 65.0 68.8
Panel B: Profit scoring models    
 LM 76.4 51.4 84.5
 \(LM^{{\lambda_{\min } ,\alpha = 1}}\) 76.9 51.2 85.2
 \(LM^{{\lambda_{\min } ,\alpha = 0}}\) 77.1 51.9 85.3
 \(LM^{{\lambda_{\min } ,\alpha_{\min } }}\) 76.8 51.2 85.1
 RFR 77.4 54.1 84.9
 NNR 75.5 57.6 81.3
  1. \(LR^{{\lambda_{\min } ,\alpha = 1}}\), \(LR^{{\lambda_{\min } ,\alpha = 0}}\), \(LR^{{\lambda_{\min } ,\alpha_{\min } }}\) are lasso, ridge and elastic net version of logistic regression, \(LM^{{\lambda_{\min } ,\alpha = 1}}\), \(LM^{{\lambda_{\min } ,\alpha = 0}}\), \(LM^{{\lambda_{\min } ,\alpha_{\min } }}\) are lasso, ridge and elastic net version of linear regression
  2. RFC random forest classification, NNC neural network classification, RRR random forest regression, NNR neural network regression