Comparative Analysis of Data Mining Classification Algorithms in Type-2 Diabetes Prediction Data Using WEKA Approach

Abstract

The goal of this paper discusses about different types of data mining classification algorithms accuracies that are widely used to extract significant knowledge from huge amounts of data. Here illustrate 20 classifications of supervised data mining algorithms base on type-2 diabetes disease dataset perspective to Bangladeshi populations. In this paper we compare 20 classification algorithms by measuring accuracies, speed and robustness of those algorithms using WEKA toolkit version 3.6.5. Accuracies of classification algorithms are measured in 3 cases like Total Training data set, 10 fold Cross Validation and Percentage Split (66% taken). Speed (CPU Execution Time) and error rate also measured as like as accuracy. Firstly checked top perform algorithms that have best outcome for different cases and then ranked top outcomes algorithms. Finally ranked best 5 algorithms among 20 algorithms based on their accuracies.

Keywords

• Accuracy
• Classification Algorithms
• Confusion Matrix
• Data Mining
• Error Rate
• Type-2 Diabetes in Bangladesh
• WEKA toolkit