Skip to main content

Table 6 Summary of applicative algorithm recommendation on different characteristic datasets

From: Empirical study of seven data mining algorithms on different characteristics of datasets for biomedical classification applications

Character of dataset NB LR kNN C4.5 SVM AB RF Represents of dataset
Small sample size     Iris, wine
High correlation       Iris, wine
Binary-class task      Breast cancer Wisconsin, Wdbc
Balanced data      Wine, breast cancer Wisconsin, Wdbc
Multi-class task      Abalone, wine quality_red
Imbalanced data      Wine quality_white
Large sample size       Adult, poker hand
Low correlation     Car evaluation, Wpbc, heart disease