Table 5 Performance parameters for the models tested
From: The use of knowledge extraction in predicting customer churn in B2B
Performance parameter | Logistic regression | Decision tree | Neural networks |
|---|---|---|---|
AUC | 0.036 | 0 | 0.075 |
AUK | 0.769 | 0.5 | 0.629 |
Kappa | 0.291 | 0 | 0.181 |
Threshold | 0.8 | 0.1 | 0.5 |
Precision | 0.220 | – | 0.117 |
Sensitivity | 0.103 | 1 | 0.591 |