Table 5 Performance, mean and (standard deviation), of churn prediction models for the using first day features using the 3-day dataset
From: Social networks for enhanced player churn prediction in mobile free-to-play games
Classifier | 3 day | |||
|---|---|---|---|---|
Precision | Recall | \({\mathbf{F}}_{1}\) | AUC | |
DecisionTree | 0.595 (0.051) | 0.781 (0.130) | 0.666 (0.033) | 0.639 (0.049) |
KNN | 0.501 (0.007) | 0.639 (0.117) | 0.557 (0.044) | 0.499 (0.036) |
RandomForest | 0.633 (0.015) | 0.751 (0.045) | 0.686 (0.025) | 0.697 (0.017) |
XGBoost | 0.619 (0.010) | 0.778 (0.075) | 0.688 (0.030) | 0.695 (0.019) |
SGD | 0.636 (0.011) | 0.603 (0.096) | 0.616 (0.058) | 0.653 (0.030) |