Comparative Analysis of Classification Algorithm on Heart Disease Dataset Using WEKA

EasyChair Preprint 3504

Abstract

The huge World number of information is offered in science, business, industry, and many other domains. These statistics can provide vital information that may be used by management for making significant decisions. Using data mining we could discover valuable details. Data mining is a convenient subject among researchers. There’s immense research that needs to be done and researchers found ease in data mining to do their research. However, this paper concentrates on the basic idea of this Data mining that's Classification methods. The operation of the classifiers examined with the support of correctly classified instances, wrongly classified instances, and time required to create the model and the end result can be revealed statistically in addition to graphically. WEKA the data mining tool is taken for this paper. The heart disease ratio is the leading ratio among death cases worldwide. It’s hard to inspect the prediction of this disease for medical experts as it’s a complex task that needs experience and knowledge. The health sector today contains hidden information that can be important in making decisions. Data mining algorithms such as Naïve Bayes, KStar, J48, and Random Forest are applied in this research for predicting heart disease. The research result shows the prediction accuracy of 83%. Data mining enables the health sector to predict patterns in the dataset.

Keyphrases: Classification, Data Mining, WEKA

@booklet{EasyChair:3504,
  author    = {Arslan Raza},
  title     = {Comparative Analysis of Classification Algorithm on Heart Disease Dataset  Using WEKA},
  howpublished = {EasyChair Preprint 3504},
  year      = {EasyChair, 2020}}