Research Article

Empirical Analysis of Machine Learning Algorithms for Multiclass Prediction

Table 2

Characteristics of selected datasets.

DatasetNo. of attributesNo. of instancesAttribute typesNo. of prediction classesDataset library

Small datasets
Horse Colic [42]27368Categorical, integer, real02UCI
Titanic [43]12891Categorical, integer, real02Kaggle
CTG [42]232126Real03UCI
Spambase [42]574601Integer, real02UCI
NYS Dept. of State Business Filings [43]249745Categorical, integer10Kaggle
Medium-sized datasets
Avila [42]1020867Real10UCI
WHO Suicide Statistics [43]643800Categorical, integer06Kaggle
Adult [42]1448842Categorical, integer02UCI
Large-sized datasets
TripAdvisor Restaurant [43]11126000Categorical, integer, real07Kaggle
NYS Nyserda [43]23223000Categorical, integer, real06Kaggle
Black Friday [43]11234000Categorical, integer10Kaggle