Skip to main content

Table 3 Performances’ summary of Data-Level methods

From: A survey on addressing high-class imbalance in big data

Technique GM TPR * TNR AUC Accuracy F-measure Big Data framework
Data-Sampling methods
 Fernandez et al. [32] Apache Hadoop and Apache Spark
  ROS 0.71
  RUS 0.70
  SMOTE 0.63
 Rio et al. [51] Apache Hadoop
  ROS 0.49
  RUS 0.48
 Triguero et al. [16] Apache Hadoop and Apache Spark
  EUS 0.67 0.67
  RUS 0.66 0.66
 Park et al. [54] Apache Hadoop
  SMOTE 0.76
 Park and Ha [56] Apache Hadoop
  SMOTE 0.81
 Chai et al. [57]
  RUS 0.99