Table 1 Summary of the data sets
Work | Location | Number of records | Number of attributes | Attributes used for training | Attribute selection | Balancing | Missing data |
|---|---|---|---|---|---|---|---|
Valter et al. [29] | Brazil | 6241 | 27 | 26 | Yes | The data set is balanced | Yes |
Hajipour et al. [32] | Iran | 2386 | Not described | 16 | Not specified | The data set is balanced | No |
Saravanou et al. [30] | USA | 12,000,000 | 128 | 128; 2; 1; 1 | No | The original data set is imbalanced, but it was balanced | No |
Baker et al. [20] | Israel | 2751 | Not described | 17 | No | The original data set is imbalanced, but it was balanced | No |
Cerqueira et al. [21] | Brazil | 293 | 114 | 4 | Yes | The data set is imbalanced | No |
Shukla et al. [10] | India; Pakistan; Congo; Zambia; Kenya; Guatemala | 588,272 | Not described | 31 | Yes | The data set is imbalanced | Yes |
Malacova et al. [14] | Australia | 960,745 | Not described | Not described | Not specified | The data set is imbalanced | No |
Sheikhtaheri et al. [22] | Iran | 1762 | Not described | 17 | Yes | The original data set is imbalanced, but it was balanced | Yes |
Podda, et al. [25] | Italy | 29,557 | Not described | 13 | Yes | The data set is imbalanced | Yes |
Batista et al. [31] | Brazil | 1,135,444 | 23 | 23 | No | The data set is imbalanced | No |
Jaskari et al. [26] | Finland | 977 | Not described | Not described | Yes | The original data set is imbalanced, but it was balanced | Yes |
Mboya et al. [12] | Tanzania | 42,319 | 32 | 20 | Yes | The original data set is imbalanced, but it was balanced | Yes |
AlShwaish et al. [33] | USA | 172,278 | Not described | Not described | Not specified | The original data set is imbalanced, but it was balanced | Yes |
Sun et al. [23] | India | 757 | Not described | 49 | No | The original data set is imbalanced, but it was balanced | Yes |
Koivu et al. [15] | USA | 12,867,146 | 26 | 17; 14; 25 | Yes | The data set is imbalanced | No |
Lee et al. [27] | USA | 31,287,801 | Not described | 34 | No | The original data set is imbalanced, but it was balanced | Yes |
Cooper et al. [28] | USA; Canada | 6499 | Not described | 68 | Yes | The data set is imbalanced | Yes |
Hsu et al. [24] | Taiwan | 1734 | Not described | 41 | Not specified | The data set is imbalanced | Yes |