Table 5 Summary of part B and part D datasets
From: Data reduction techniques for highly imbalanced medicare Big Data
Dataset | Instance count | Fraudulent | Ratio fraudulent | Number of features |
|---|---|---|---|---|
Part D | 5,344,106 | 3,700 | 0.0693% | 80 |
Part B | 8,669,497 | 3,954 | 0.0456% | 82 |